Search

Due to the lack of life experience and situational experience, it is difficult to arouse pupils' inner motivation and interest in writing. Therefore, the early stage of Chinese writing may be a challenge for Chinese pupils. In order to solve this problem, a spherical video‐based virtual reality (SVVR) experience learning system was developed to help pupils improve their writing performance and interest. To evaluate the effectiveness of the proposed approach, an experiment was carried out in a primary school in Zhejiang province, China. First, a writing pretest was administered in two grade 4 classes. The researchers then randomly selected 40 pupils of about 10 years old with similar writing abilities, and assigned them to an experimental group, which used the SVVR learning method, and a control group, which used the traditional learning method. The researchers observed and recorded the pupils' writing process and then, interviewed them. The results showed that there was a significant difference in the comprehensive writing performance of the two groups (F = 6.272; p =.017 <.05). The mean of the experimental group (Mean = 73.85) was higher than that of the control group (Mean = 70.00). Moreover, there were significant differences between the two groups in terms of the thematic coherence, structural integrity and linguistic expressiveness of their writing performance. However, there was no significant difference in the achievement of creative thinking. In the experimental group, different levels of learning behavior engagement could affect the structural integrity and language expression of writing achievements, and the degree of writing learning behavior engagement was highly correlated with reading time. Through the interviews, it was found that the pupils in the experimental group were more satisfied with the SVVR learning method than the control group pupils were with the traditional learning method. Practitioner NotesWhat is already known about this topic? Spherical video‐based virtual reality (SVVR) set a simulated environment enabling students to have in‐depth experience in learning contexts.Most SVVR studies focused on speaking and writing in middle schools and colleges, while its impacts on young children's writing performance is generally ignored.What this paper adds? An SVVR system based on experiencing learning theory was developed to promote young students' in‐depth experience and perception in descriptive paper writing.The proposed approach promoted students' writing performances, writing experience and learning behavior engagement.Implications for practice and/or policy SVVR is a potential technology for implementing experiential learning activities, especially in improving thematic coherence, structural integrity and linguistic expressiveness.It is worth promoting such a low‐tech and low‐cost experiential learning approach to other courses. [ABSTRACT FROM AUTHOR]

The paper introduces the student‐coined term digital instinct which describes students' disposition to resorting to digital technology for solving problems and doing school assignments. Taking cues from the term digital instinct, the paper describes a student perspective on digital literacy emerging from 100 lived experience descriptions and interviews with 37 Danish upper secondary students. The findings show that students' digital practice is characterised by experience‐based, intuitive and familiar use of technologies. Most notably, students employ digital technologies as cognitive partners that help them carry on with assignments that they initially did not understand, but that they were able to complete with the help of the computer. The study examines the nature of this partnership through the words of the students and identifies how technologies expand student agency but fall short of a reflective use of digital technologies. Recognising the strengths and weaknesses of students' digital practices may inform the concept of digital literacy and encourage teachers to acknowledge the digital instinct as a steppingstone to foster students' reflective use of digital technologies. Practitioner notesWhat is already known about this topic Students have inadequate command of digital literacies as described in curricular terminology.Students have positive as well as negative perceptions of the value and usefulness of digital technologies in school.Students both over‐ and underestimate their own digital literacies.What this paper adds Students have a fundamental utilitarian conception of digital technologies that either make schoolwork easier or more difficult, and they do not articulate that their use of digital technologies provides them with digital literacies.Students' conception of a digital instinct describes an intuitive and familiar, albeit unreflected, use of technologies where students employ experience‐based and self‐taught methods for using digital technologies.The digital instinct accounts for a feeling of agency among students, manifested in a widespread confidence that they can do assignments and solve problems when they make use of their computer.Implications for practice and/or policy Curricular terminologies struggle to capture what students can and cannot do with technology, and how much they understand the underlying technology.Teachers can involve and build on students' experience‐based digital practices as a starting point for developing digital literacy among students—also as an entry to a curricular perspective.Teachers should acknowledge students' conception of a 'digital instinct' as an important disposition in its own right. [ABSTRACT FROM AUTHOR]

Over the last two decades, the educational use of digital devices, including digital assessments, has become a regular feature of teaching in primary education in the Netherlands. However, researchers have not reached a consensus about the so‐called "mode effect," which refers to the possible impact of using computer‐based tests (CBT) instead of paper‐and‐pencil‐based tests (PBT) to assess student performance. Some researchers suggest that the occurrence of a mode effect might be related to the type of device used, the subject being assessed and the characteristics of both the test and the students taking the test. The international TIMSS 2019 Equivalence Study offered the opportunity to explore possible performance differences between a PBT and a tablet assessment in mathematics and science among Dutch primary school students. In the spring of 2017, the TIMSS PBT and tablet test were administered to 532 grade‐four Dutch students. Item response theory was used to explore potential mode effects. This exploration revealed no significant differences in the student ability scales between the paper and the tablet tests for mathematics and science. Also, no systematic mode effects were found for the items with high reading demand. A marginal difference was found for girls outperforming boys on the TIMSS tablet test, although no gender differences in achievement were found for the PBT. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) and natural language processing technologies have fuelled the growth of Pedagogical Conversational Agents (PCAs) with empathic conversational capabilities. However, no systematic literature review has explored the intersection between conversational agents, education and emotion. Therefore, this study aimed to outline the key aspects of designing, implementing and evaluating these agents. The data sources were empirical studies, including peer‐reviewed conference papers and journal articles, and the most recent publications, from the ACM Digital Library, IEEE Xplore, ProQuest, ScienceDirect, Scopus, SpringerLink, Taylor & Francis Online, Web of Science and Wiley Online Library. The remaining papers underwent a rigorous quality assessment. A filter study meeting the objective was based on keywords. Comparative analysis and synthesis of results were used to handle data and combine study outcomes. Out of 1162 search results, 13 studies were selected. The results indicate that agents promote dialogic learning, proficiency in knowledge domains, personalized feedback and empathic abilities as essential design principles. Most implementations employ a quantitative approach, and two variables are used for evaluation. Feedback types play a vital role in achieving positive results in learning performance and student perceptions. The main limitations and gaps are the time range for literature selection, the level of integration of the empathic field and the lack of a detailed development stage report. Moreover, future directions are the ethical implications of agents operating beyond scheduled learning times and the adoption of Responsible AI principles. In conclusion, this review provides a comprehensive framework of empathic PCAs, mostly in their evaluation. The systematic review registration number is osf.io/3xk6a.Practitioner notesWhat is already known about this topicEmotions play a pivotal role in shaping the interaction process, making it essential to consider them when designing methodological strategies or learning tools.Empathic Pedagogical Conversational Agents (PCAs) have emerged as a crucial approach for enhancing and personalizing the learning experience (24/7) for pupils and supporting human teachers in their teaching process.Despite the creation of numerous empathic PCAs, there is a scarcity of Systematic Literature Reviews (SLRs) on their application in the educational field, particularly concerning the integration of emotional abilities in combination with the competencies of each subject.What this paper addsIt offers new insights into the design principles underlying the integration of the empathic field.It reviews different approaches for incorporating students' prior knowledge in real time.It provides a comprehensive and up‐to‐date overview of the research designs used for implementation, including quantitative, qualitative and mixed methods.It examines the factors that influence the effectiveness of empathic PCA in teaching and learning.It evaluates the types of feedback that enhance the impact of the empathic field on learning outcomes.Implications for practice and/or policyIt is crucial to grasp the topics that this paper introduces in order to effectively integrate new learning tools into any context.Techno‐pedagogical designers seeking to gain insights into empathic PCAs will find immense value in this SLR, as it comprehensively covers each stage of the process.For future research endeavours, this study offers a wealth of ideas to draw upon, enabling researchers to address the challenges outlined and explore new avenues of investigation. [ABSTRACT FROM AUTHOR]

The article seeks to develop a better understanding of the contribution of materiality in a discourse between a creator (content producer) and an interface, dealing with analogue and digital artefacts. Focus is in the materiality of the two different art‐creation learning processes, acrylic painting and digital painting. The objective of this paper is to consider especially the affect and meaning of these two different content creation modalities and intra‐action within that. Through reflective autoethnographic consideration, the purpose is to consider the essences of materials manifesting and modulating the processes of content creation as a posthumanist phenomenon. It will be shown that the creation processes with paper are more experimental whereas the processes with digital screen are more playful. There is a growing need to deeper understand the cultural change of material cultures and the people's intra‐action with the materials also enabling arts creation. This paper will widen our limited understanding and deepen our theoretical perspectives of the essence of materials which then avails confronting analogue and digital when developing teaching and learning in the posthuman era especially in early education. Practitioner NotesWhat is already known about this topic There is a growing interest in the new materialism and posthuman thinking amongst educational technology research and development.Reading analogue versus digital is well‐documented.What this paper adds New materialist thinking offers a useful perspective in education for looking at the essence of analogue and digital materiality modulating content creation.Characterising the nuances in analogue and digital production can help in evaluating their educational potential.Implications for practice and/or policy As practitioners we should critically question the political vision of education digitalisation especially concerning early childhood education.There is a need to move beyond debates about analogue versus digital to look at more specific examples of their advantages (and disadvantages) in developing posthumanist education and intra‐active pedagogy especially for young children. [ABSTRACT FROM AUTHOR]

Highly cited papers can be representative of the latest changes in specific research issues, as they reflect the important issues or research trends that researchers have paid attention to recently. Through reading highly cited papers, researchers can identify some important issues for consideration in their own research, which can then catch other researchers' eyes easily and efficiently. In order to explore the feature of the latest changes in mobile learning, in this study, a review of the top 100 highly cited mobile learning papers was conducted. According to the review, four advantages were identified from the highly cited mobile learning studies: proposing new learning strategies, applying mobile learning to seldom‐considered subjects, applying mobile learning to seldom‐investigated domains and investigating seldom‐discussed issues. It was found that the studies focused more on comparing different mobile learning modes for finding more effective mobile learning approaches rather than comparing the impacts of mobile learning with traditional instruction. Moreover, the studies focused more on learners' higher order thinking performance and learning behaviors. Some suggestions, differing from those presented by previous mobile learning reviews, are provided as reference for researchers to conduct related research. Practitioner NotesWhat is already known about this topic Mobile learning has been regarded as a tool for improving learners' learning and bridging students' learning in class and in the field.Research trends can be highlighted and provide a more accurate view of the publication patterns.Highly cited papers can be used to identify the advance of the research foci.What this paper adds Most highly cited studies mainly focused on comparing the different mobile learning modes to find more effective approaches for conducting mobile learning activities.The mobile learning places have changed from classrooms to real‐world contexts; in addition, the number of across‐context studies is increasing.The highly cited papers started to focus more on learners' higher‐order thinking performance and learning behaviors.Implications for practice and/or policy Researchers can consider proposing new learning strategies, applying mobile learning to seldom‐considered subjects, applying mobile learning to seldom‐investigated domains, and investigating seldom‐discussed issues.Adopting mixed methods is becoming the mainstream of mobile learning studies.Several seldom‐discussed issues, such as higher order thinking, collaboration/communication skills, and learning behaviors are potential mobile learning research topics. [ABSTRACT FROM AUTHOR]

There is nothing less about paper and its use when it comes to academic study as we experience increasingly converging media spaces and functionalities of online applications within the screens of our laptops, mobile phones and tablet devices. The paper persists, and the paperless office, classroom and pedagogy become nothing but pure rhetoric. Hence, it is most pertinent to focus on paper and its 'stickiness' in maintaining educational structures and practices. Usually hidden from view or neglected in educational technology studies is a consideration on how we think and interact not only with our mind but also with our heads and limbs. This paper will argue that paper has a composite place or bearing, a kind of stickiness to our technologised bodies, digital mobilities and hybrid practices in what I have coined here as papier-mach(in)e. This claim will be supported by evidence that demonstrates how we simply think both practically and pathically and that our mobilities in media and physical spaces are in one form or another meshed with paper. In fact, a drive towards a paperless classroom or pedagogy is without much foundation when it comes to mobilising a sustainable agenda for technology-enhanced learning. [ABSTRACT FROM AUTHOR]

Computational thinking is a necessary skill for the 21st century. While previously examined in computer‐rich settings, researchers are increasingly studying computational thinking in unplugged environments such as board games. Focusing on the African board game Songo, this study shows that computational thinking practices are embedded in Songo board gameplay and interact with the cultural context. The study also reveals a computing practice peculiar to Songo gameplay, songoputation. This paper suggests that researchers can benefit from exploring computational thinking and computing practices beyond board games in western contexts. Practitioner notesWhat is already known about this topicComputational thinking can be cultivated in non‐digital environments.Board games are spaces where computational thinking can be developed.The relationship between African board games and computational thinking is still unknown.What this paper addsAfrican board games such as Songo are spaces where players engage with computational thinking and songoputationCulture informs computational thinking practices players engaging in when playing Songo.Computational thinking is not a new practice and should be explored in different culture contexts and settings.Implications for practice and/or policyAfrican board games should be used to develop computational thinking skills.Board games should be used to foster computational thinking skills among students in context with limited access to digital technology. [ABSTRACT FROM AUTHOR]

Nowadays the size of university classes along with the growing number of students to be tested for final examination raise unprecedented challenges relating to the management, monitoring and evaluation of learning. Technology may provide some solutions that deserve to be investigated. This paper explores the potentialities and limitations of Computer‐Based Testing (CBT), specifically BYOD e‐test, compared to traditional Paper‐Based Testing (PBT) to verify whether, and to what extent, an electronic mode of assessment can become a suitable alternative to PBT. It is based on a study carried out at the University of Florence during 2016/17. 606 students participated in the study, of whom 443 opted for CBT using their own devices, while 163 preferred PBT. Participants who experienced CBT also answered a survey on perceptions, self‐efficacy and satisfaction. The results show that students' performances were better with CBT, and that a positive relationship exists between the perceived level of self‐efficacy and the propensity to adopt digital tests. In addition, students greatly appreciated the electronic system, especially for the possibility of immediate feedback. Some critical issues emerged relating to on‐screen reading, which suggests the need for careful design of testing tools. [ABSTRACT FROM AUTHOR]

Learning with games requires two types of information, namely domain‐specific information and game‐specific information. Presenting these two types of information together with gameplay may pose a heavy demand on cognitive resources. This study investigates how timing of information presentation affects cognition (ie, mental effort and performance), motivation (ie, achievement goals) and emotion (ie, achievement emotions). Participants were secondary school students (N = 145). Participants participated in a 2 × 2 factorial experiment with two factors—timing of domain‐specific information presentation and timing of game‐specific information presentation, either before or during gameplay. We measured mental effort, chemistry knowledge, time on task, achievement goals and achievement emotions. Multiple regression and robust regression revealed that presenting domain‐specific information before gameplay promoted higher approach goals, higher avoidance goals and more enjoyment than presenting it during gameplay. There was no difference between presenting game‐specific information before gameplay and during gameplay except for performance‐avoidance goals. We conclude that timing of information presentation affects motivational and emotional processes and outcomes and that students feel more motivated and enjoyed when domain‐specific information is presented before learning than during learning. Educators may change the timing of domain‐specific information presentation accordingly. Practitioner notes What is already known about this topic Well‐designed game‐based learning can increase learning. Game‐based learning needs effective instructional design features. What this paper adds One instructional design feature, timing of information presentation, affects motivation and emotion in game‐based learning. Students feel more motivated and enjoyed when domain‐specific information is presented before learning than during learning. This study is one of the first to focus on cognitive, motivational and emotional processes and outcomes, and their interconnections. Implications for practice and policy Educators would do well to present domain‐specific information before learning than during learning. Researchers on instructional design features should attend to all cognitive, motivational and emotional processes and outcomes instead of just one or two. What is already known about this topic Well‐designed game‐based learning can increase learning. Game‐based learning needs effective instructional design features. What this paper adds One instructional design feature, timing of information presentation, affects motivation and emotion in game‐based learning. Students feel more motivated and enjoyed when domain‐specific information is presented before learning than during learning. This study is one of the first to focus on cognitive, motivational and emotional processes and outcomes, and their interconnections. Implications for practice and policy Educators would do well to present domain‐specific information before learning than during learning. Researchers on instructional design features should attend to all cognitive, motivational and emotional processes and outcomes instead of just one or two. [ABSTRACT FROM AUTHOR]

Educational outcomes from traditionally underrepresented groups are generally worse than for their more advantaged peers. This problem is typically known as the awarding gap (we use the term awarding gap over ‘attainment gap’ as attainment places the responsibility on students to attain at equal levels) and continues to pose a challenge for educational systems across the world. While Learning Analytics (LA) dashboards help identify patterns contributing to the awarding gap, they often lack stakeholder involvement, offering very little support to institutional Equality, Diversity and Inclusion (EDI) leads or educators to pinpoint and address these gaps. This paper introduces an innovative EDI LA dashboard, co‐created with diverse stakeholders. Rigorously evaluated, the dashboard provides fine‐grained insights and course‐level analysis, empowering institutions to effectively address awarding gaps and contribute to a diverse and inclusive higher education landscape. Practitioners notes What is already known about this topic Traditionally underrepresented groups face educational disparities, commonly known as the awarding gap. Underachievement is a complex multi‐dimensional problem and cannot be solely attributable to individual student deficiencies. LA dashboards targeting this specific problem are often not public, there is little research about them, and are frequently designed with little involvement of educational stakeholders. What this paper adds Pioneers the introduction of a dashboard specifically designed to address the awarding gap problem. Emphasises the significant data needs of educational stakeholders in tackling awarding gaps. Expands the design dimensions of Learning Analytics (LA) by introducing a specific design approach rooted in established user experience (UX) design methods. Implications for practice and/or policy Insights from this study will guide practitioners, designers, and developers in creating AI‐based educational systems to effectively target the awarding gap problem. What is already known about this topic Traditionally underrepresented groups face educational disparities, commonly known as the awarding gap. Underachievement is a complex multi‐dimensional problem and cannot be solely attributable to individual student deficiencies. LA dashboards targeting this specific problem are often not public, there is little research about them, and are frequently designed with little involvement of educational stakeholders. What this paper adds Pioneers the introduction of a dashboard specifically designed to address the awarding gap problem. Emphasises the significant data needs of educational stakeholders in tackling awarding gaps. Expands the design dimensions of Learning Analytics (LA) by introducing a specific design approach rooted in established user experience (UX) design methods. Implications for practice and/or policy Insights from this study will guide practitioners, designers, and developers in creating AI‐based educational systems to effectively target the awarding gap problem. [ABSTRACT FROM AUTHOR]

Large language models (LLMs) are increasingly adopted in educational contexts to provide personalized support to students and teachers. The unprecedented capacity of LLM‐based applications to understand and generate natural language can potentially improve instructional effectiveness and learning outcomes, but the integration of LLMs in education technology has renewed concerns over algorithmic bias, which may exacerbate educational inequalities. Building on prior work that mapped the traditional machine learning life cycle, we provide a framework of the LLM life cycle from the initial development of LLMs to customizing pre‐trained models for various applications in educational settings. We explain each step in the LLM life cycle and identify potential sources of bias that may arise in the context of education. We discuss why current measures of bias from traditional machine learning fail to transfer to LLM‐generated text (eg, tutoring conversations) because text encodings are high‐dimensional, there can be multiple correct responses, and tailoring responses may be pedagogically desirable rather than unfair. The proposed framework clarifies the complex nature of bias in LLM applications and provides practical guidance for their evaluation to promote educational equity. Practitioner notes What is already known about this topic The life cycle of traditional machine learning (ML) applications which focus on predicting labels is well understood. Biases are known to enter in traditional ML applications at various points in the life cycle, and methods to measure and mitigate these biases have been developed and tested. Large language models (LLMs) and other forms of generative artificial intelligence (GenAI) are increasingly adopted in education technologies (EdTech), but current evaluation approaches are not specific to the domain of education. What this paper adds A holistic perspective of the LLM life cycle with domain‐specific examples in education to highlight opportunities and challenges for incorporating natural language understanding (NLU) and natural language generation (NLG) into EdTech. Potential sources of bias are identified in each step of the LLM life cycle and discussed in the context of education. A framework for understanding where to expect potential harms of LLMs for students, teachers, and other users of GenAI technology in education, which can guide approaches to bias measurement and mitigation. Implications for practice and/or policy Education practitioners and policymakers should be aware that biases can originate from a multitude of steps in the LLM life cycle, and the life cycle perspective offers them a heuristic for asking technology developers to explain each step to assess the risk of bias. Measuring the biases of systems that use LLMs in education is more complex than with traditional ML, in large part because the evaluation of natural language generation is highly context‐dependent (eg, what counts as good feedback on an assignment varies). EdTech developers can play an important role in collecting and curating datasets for the evaluation and benchmarking of LLM applications moving forward. What is already known about this topic The life cycle of traditional machine learning (ML) applications which focus on predicting labels is well understood. Biases are known to enter in traditional ML applications at various points in the life cycle, and methods to measure and mitigate these biases have been developed and tested. Large language models (LLMs) and other forms of generative artificial intelligence (GenAI) are increasingly adopted in education technologies (EdTech), but current evaluation approaches are not specific to the domain of education. What this paper adds A holistic perspective of the LLM life cycle with domain‐specific examples in education to highlight opportunities and challenges for incorporating natural language understanding (NLU) and natural language generation (NLG) into EdTech. Potential sources of bias are identified in each step of the LLM life cycle and discussed in the context of education. A framework for understanding where to expect potential harms of LLMs for students, teachers, and other users of GenAI technology in education, which can guide approaches to bias measurement and mitigation. Implications for practice and/or policy Education practitioners and policymakers should be aware that biases can originate from a multitude of steps in the LLM life cycle, and the life cycle perspective offers them a heuristic for asking technology developers to explain each step to assess the risk of bias. Measuring the biases of systems that use LLMs in education is more complex than with traditional ML, in large part because the evaluation of natural language generation is highly context‐dependent (eg, what counts as good feedback on an assignment varies). EdTech developers can play an important role in collecting and curating datasets for the evaluation and benchmarking of LLM applications moving forward. [ABSTRACT FROM AUTHOR]

A key goal of educational institutions around the world is to provide inclusive, equitable quality education and lifelong learning opportunities for all learners. Achieving this requires contextualized approaches to accommodate diverse global values and promote learning opportunities that best meet the needs and goals of all learners as individuals and members of different communities. Advances in learning analytics (LA), natural language processes (NLP), and artificial intelligence (AI), especially generative AI technologies, offer potential to aid educational decision making by supporting analytic insights and personalized recommendations. However, these technologies also raise serious risks for reinforcing or exacerbating existing inequalities; these dangers arise from multiple factors including biases represented in training datasets, the technologies' abilities to take autonomous decisions, and processes for tool development that do not centre the needs and concerns of historically marginalized groups. To ensure that Educational Decision Support Systems (EDSS), particularly AI‐powered ones, are equipped to promote equity, they must be created and evaluated holistically, considering their potential for both targeted and systemic impacts on all learners, especially members of historically marginalized groups. Adopting a socio‐technical and cultural perspective is crucial for designing, deploying, and evaluating AI‐EDSS that truly advance educational equity and inclusion. This editorial introduces the contributions of five papers for the special section on advancing equity and inclusion in educational practices with AI‐EDSS. These papers focus on (i) a review of biases in large language models (LLMs) applications offers practical guidelines for their evaluation to promote educational equity, (ii) techniques to mitigate disparities across countries and languages in LLMs representation of educationally relevant knowledge, (iii) implementing equitable and intersectionality‐aware machine learning applications in education, (iv) introducing a LA dashboard that aims to promote institutional equality, diversity, and inclusion, and (v) vulnerable student digital well‐being in AI‐EDSS. Together, these contributions underscore the importance of an interdisciplinary approach in developing and utilizing AI‐EDSS to not only foster a more inclusive and equitable educational landscape worldwide but also reveal a critical need for a broader contextualization of equity that incorporates the socio‐technical questions of what kinds of decisions AI is being used to support, for what purposes, and whose goals are prioritized in this process. [ABSTRACT FROM AUTHOR]

Spatial thinking is essential for nurturing spatially literate graduates in tertiary education. However, there is limited research on individual differences in cognitive processes and their impact on spatial problem solving in disciplinary contexts. This study aimed to investigate cognitive processes involved in spatial thinking in geography majors using a web‐based geographic information systems (GIS) mapping tool. The results revealed three clusters characterised by distinctive cognitive processes: spatial analytic, spatial diagrammatic and alternative. Each cluster adopted unique spatial strategies to solve problems with web‐based GIS. Notably, spatial analytic learners demonstrated the most optimal profile, resulting in high spatial task performance. These findings have implications for maximising students' learning potential in spatial thinking in the tertiary classroom, optimising performance outcomes in spatial problem solving and building intelligent tutoring systems for adaptive learning. Practitioner notes What is already known about this topic There are individual differences in spatial reasoning. The processes of spatial thinking may have an impact on learners' spatial performance outcomes. What this paper adds Three clusters characterised by distinctive processes of spatial thinking were identified: spatial analytic, spatial diagrammatic and alternative. Each cluster adopted unique spatial strategies to solve problems with web‐based GIS. Spatial analytic learners demonstrated the optimal profile, resulting in high‐level spatial performance, whereas alternative learners exhibited the maladaptive profile, which was associated with low task outcomes. Implications for practice and/or policy Web‐based GIS mapping tools make it possible to track the processes of spatial thinking that have remained largely unexplored. Cluster analysis and lag sequential analysis reveal differences in spatial reasoning, aiding educators in maximising the potential for university students to learn spatial thinking and optimising performance outcomes in spatial problem solving. Our findings could inform learning technology designers to build adaptive learning applications in which students receive automatic feedback and tailored support while completing spatial tasks at their own pace. What is already known about this topic There are individual differences in spatial reasoning. The processes of spatial thinking may have an impact on learners' spatial performance outcomes. What this paper adds Three clusters characterised by distinctive processes of spatial thinking were identified: spatial analytic, spatial diagrammatic and alternative. Each cluster adopted unique spatial strategies to solve problems with web‐based GIS. Spatial analytic learners demonstrated the optimal profile, resulting in high‐level spatial performance, whereas alternative learners exhibited the maladaptive profile, which was associated with low task outcomes. Implications for practice and/or policy Web‐based GIS mapping tools make it possible to track the processes of spatial thinking that have remained largely unexplored. Cluster analysis and lag sequential analysis reveal differences in spatial reasoning, aiding educators in maximising the potential for university students to learn spatial thinking and optimising performance outcomes in spatial problem solving. Our findings could inform learning technology designers to build adaptive learning applications in which students receive automatic feedback and tailored support while completing spatial tasks at their own pace. [ABSTRACT FROM AUTHOR]

Conversational user interfaces (CUI), including voice interfaces, which allow users to converse with computers via voice, are gaining wide popularity. VoiceBots allow users to receive a response in real‐time, regardless of the communication device. VoiceBots have been explored in fields such as customer service to automate repetitive queries and help reduce redundant tasks; however, they have not been widely applied in the classroom. This study aimed to explore the effects of VoiceBot implementation on student learning. A pre‐test–post‐test design was implemented with 65 participating undergraduate students in multimedia programming who were randomly allocated to scenarios representing a 2 × 2 design (experimental and control cohorts). Data were collected using an academic achievement test and semi‐structured interviews, which allowed for a more in‐depth analysis of the students' experiences with the VoiceBot. The results showed that how the VoiceBot was applied positively influenced student learning in the experimental cohort. Moreover, the focus group data demonstrated that the VoiceBot can be a valuable assistant for students and could be easily replicated in other courses. To the best of our knowledge, this study was the first to use VoiceBot to engage undergraduate students in Ghana, thus contributing to the growing literature stream on the development of VoiceBots to improve student learning experiences. This study elucidates the design process using a zero‐coding technique, which is considered a suitable approach for educational institutions with limited resources. Practitioner notes What is already known about this topic Conversational user interfaces (CUIs), including voice interfaces, have gained popularity and are used to interact with computers through natural language. VoiceBots have been utilised in various fields such as customer service to automate tasks and reduce redundancy. Instant messaging systems such as WhatsApp and Telegram have been used for communication in educational contexts. Advances in artificial intelligence (AI) and natural language processing (NLP) have led to significant improvements in voice‐enabled CUIs (VoiceBots). Existing studies indicate that chatbots affect students' motivation, learning experiences, and achievements; however, research on using VoiceBots for learning improvement is limited. What this paper adds A VoiceBot was introduced as an assistant to facilitate learning in a multimedia programming course. The study used an experimental design with an experimental cohort using a WhatsApp group platform equipped with a zero‐coding VoiceBot and a control cohort without the bot. The study found that students interacting with VoiceBot demonstrated better learning achievement than the control group. The study also provides clear suggestions on integrating VoiceBots into educational institutions. Implications for practice and/or policy The study's findings suggest that VoiceBots can play a significant role in improving student learning achievements, especially in subjects such as multimedia programming. Educational institutions could establish learning design and technology centres with subject matter experts to integrate VoiceBots effectively into the learning process. Instructors must possess adequate technological proficiency to engage students with VoiceBots and targeted in‐service training may be necessary. Future research can explore VoiceBot use across various academic domains and levels of education, analyse the impact of usage patterns on learning outcomes, and assess its long‐term effects on student engagement and motivation. What is already known about this topic Conversational user interfaces (CUIs), including voice interfaces, have gained popularity and are used to interact with computers through natural language. VoiceBots have been utilised in various fields such as customer service to automate tasks and reduce redundancy. Instant messaging systems such as WhatsApp and Telegram have been used for communication in educational contexts. Advances in artificial intelligence (AI) and natural language processing (NLP) have led to significant improvements in voice‐enabled CUIs (VoiceBots). Existing studies indicate that chatbots affect students' motivation, learning experiences, and achievements; however, research on using VoiceBots for learning improvement is limited. What this paper adds A VoiceBot was introduced as an assistant to facilitate learning in a multimedia programming course. The study used an experimental design with an experimental cohort using a WhatsApp group platform equipped with a zero‐coding VoiceBot and a control cohort without the bot. The study found that students interacting with VoiceBot demonstrated better learning achievement than the control group. The study also provides clear suggestions on integrating VoiceBots into educational institutions. Implications for practice and/or policy The study's findings suggest that VoiceBots can play a significant role in improving student learning achievements, especially in subjects such as multimedia programming. Educational institutions could establish learning design and technology centres with subject matter experts to integrate VoiceBots effectively into the learning process. Instructors must possess adequate technological proficiency to engage students with VoiceBots and targeted in‐service training may be necessary. Future research can explore VoiceBot use across various academic domains and levels of education, analyse the impact of usage patterns on learning outcomes, and assess its long‐term effects on student engagement and motivation. [ABSTRACT FROM AUTHOR]

Self‐regulated learning (SRL) is an essential skill to achieve one's learning goals. This is particularly true for online learning environments (OLEs) where the support system is often limited compared to a traditional classroom setting. Likewise, existing research has found that learners often struggle to adapt their behaviour to the self‐regulatory demands of OLEs. Even so, existing SRL analysis tools have limited utility for real‐time or individualised support of a learner's SRL strategy during a study session. Accordingly, we explore a reinforcement learning based approach to learning optimal SRL strategies for a specific learning task. Specifically, we utilise the sequences of SRL processes acted by 44 participants, and their assessment scores for a prescribed learning task, in a purpose‐built OLE to develop a long short‐term memory (LSTM) network based reward function. This is used to train a reinforcement learning agent to find the optimal sequence of SRL processes for the learning task. Our findings indicate that the developed agents were able to effectively select SRL processes so as to maximise a prescribed learning goal as measured by predicted assessment score and predicted knowledge gains. The contributions of this work will facilitate the development of a tool which can detect sub‐optimal SRL strategy in real‐time and enable individualised SRL focused scaffolding. Practitioner notesWhat is already known about this topic Learners often fail to adequately adapt their behavior to the self‐regulatory demands of e‐Learning environments.In order to promote effective Self‐regulated learning (SRL) capabilities, researchers and educators need tools that are able to analyze and diagnose a learner's SRL strategy use.Current methods for SRL analysis are more often descriptive as opposed to prescriptive and have limited utility for real‐time analysis or support of a learner's SRL behavior.What this paper adds This paper proposes the use of Reinforcement Learning for prescriptive analytics of SRL. We train a Reinforcement Learning agent on sequences of SRL processes acted by learners in order to learn the optimal SRL strategy for a given learning task.Implications for practice and/or policy Our work will facilitate the development of a tool which can detect sub‐optimal SRL strategy in real‐time and enable individualized SRL focused scaffolding.The implications of our work can aid in course design by predicting the self‐regulatory load imposed by a given task.The ability to model SRL strategies using Reinforcement Learning can be extended to simulate or test SRL theories. [ABSTRACT FROM AUTHOR]

A core focus of self‐regulated learning (SRL) research lies in uncovering methods to empower learners within digital learning environments. As digital technologies continue to evolve during the current hype of artificial intelligence (AI) in education, the theoretical, empirical and methodological nuances to support SRL are emerging and offering new ways for adaptive support and guidance for learners. Such affordances offer a unique opportunity for personalised learning experiences, including adaptive interventions. Exploring the application of adaptivity to enhance SRL is an important and emerging area of research that requires further attention. This editorial introduces the contributions of seven papers for the special section on adaptive support for SRL within digital learning environments. These papers explore various themes related to enhancing SRL strategies through technological interventions, offering valuable insights and paving the way for future advancements in this dynamic area. [ABSTRACT FROM AUTHOR]

In recent years, AI technologies have been developed to promote students' self‐regulated learning (SRL) and proactive learning in digital learning environments. This paper discusses a comparative study between generative AI‐based (SRLbot) and rule‐based AI chatbots (Nemobot) in a 3‐week science learning experience with 74 Secondary 4 students in Hong Kong. The experimental group used SRLbot to maintain a regular study habit and facilitate their SRL, while the control group utilized rule‐based AI chatbots. Results showed that SRLbot effectively enhanced students' science knowledge, behavioural engagement and motivation. Quantile regression analysis indicated that the number of interactions significantly predicted variations in SRL. Students appreciated the personalized recommendations and flexibility of SRLbot, which adjusted responses based on their specific learning and SRL scenarios. The ChatGPT‐enhanced instructional design reduced learning anxiety and promoted learning performance, motivation and sustained learning habits. Students' feedback on learning challenges, psychological support and self‐regulation behaviours provided insights into their progress and experience with this technology. SRLbot's adaptability and personalized approach distinguished it from rule‐based chatbots. The findings offer valuable evidence for AI developers and educators to consider generative AI settings and chatbot design, facilitating greater success in online science learning. Practitioner notesWhat is already known about this topic AI technologies have been used to support student self‐regulated learning (SRL) across subjects.SRL has been identified as an important aspect of student learning that can be developed through technological support.Generative AI technologies like ChatGPT have shown potential for enhancing student learning by providing personalized guidance and feedback.What this paper adds This paper reports on a case study that specifically examines the effectiveness of ChatGPT in promoting SRL among secondary students.The study provides evidence that ChatGPT can enhance students' science knowledge, motivation and SRL compared to a rule‐based AI chatbot.The study offers insights into how ChatGPT can be used as a tool to facilitate SRL and promote sustained learning habits.Implications for practice and/or policy The findings of this study suggest that educators should consider the potential of ChatGPT and other generative AI technologies to support student learning and SRL.Educators and students should be aware of the limitations of AI technologies and ensure that they are used appropriately to generate desired responses.It is also important to equip teachers and students with AI competencies to enable them to use AI for learning and teaching. [ABSTRACT FROM AUTHOR]

Effective collaboration and teamwork skills are critical in high‐risk sectors, as deficiencies in these areas can result in injuries and risk of death. To foster the growth of these vital skills, immersive learning spaces have been created to simulate real‐world scenarios, enabling students to safely improve their teamwork abilities. In such learning environments, multiple dialogue segments can occur concurrently as students independently organise themselves to tackle tasks in parallel across diverse spatial locations. This complex situation creates challenges for educators in assessing teamwork and for students in reflecting on their performance, especially considering the importance of effective communication in embodied teamwork. To address this, we propose an automated approach for generating teamwork analytics based on spatial and speech data. We illustrate this approach within a dynamic, immersive healthcare learning environment centred on embodied teamwork. Moreover, we evaluated whether the automated approach can produce transcriptions and epistemic networks of spatially distributed dialogue segments with a quality comparable to those generated manually for research objectives. This paper makes two key contributions: (1) it proposes an approach that integrates automated speech recognition and natural language processing techniques to automate the transcription and coding of team communication and generate analytics; and (2) it provides analyses of the errors in outputs generated by those techniques, offering insights for researchers and practitioners involved in the design of similar systems.Practitioner notesWhat is currently known about this topic Immersive learning environments simulate real‐world situations, helping students improve their teamwork skills.In these settings, students can have multiple simultaneous conversations while working together on tasks at different physical locations.The dynamic nature of these interactions makes it hard for teachers to assess teamwork and communication and for students to reflect on their performance.What this paper adds We propose a method that employs multimodal learning analytics for automatically generating teamwork‐related insights into the content of student conversations.This data processing method allows for automatically transcribing and coding spatially distributed dialogue segments generated from students working in teams in an immersive learning environment and enables downstream analysis.This approach uses spatial analytics, natural language processing and automated speech recognition techniques.Implications for practitioners Automated coding of dialogue segments among team members can help create analytical tools to assist in evaluating and reflecting on teamwork.By analysing spatial and speech data, it is possible to apply learning analytics advancements to support teaching and learning in fast‐paced physical learning spaces where students can freely engage with one another. [ABSTRACT FROM AUTHOR]

Adaptive learning technologies are closely related to learners' self‐regulatory processes in individual and collaborative learning. This study presents the outcomes of a systematic literature review of empirical evidence on adaptive learning environments to foster self‐regulation and shared regulation of learning in collaborative settings. We provide an overview of what and how adaptive technologies have been used to understand and promote self‐regulated learning in collaborative contexts. A search resulted in 38 papers being analysed. Specifically, we identified the seven main objectives (feedback and scaffolding, self‐regulatory skills and strategies, learning trajectories, collaborative learning processes, adaptation and regulation, self‐assessment, and help‐seeking behaviour) that the adaptive technology research has been focusing on. We also summarize the implications derived from the reviewed papers and frame them within seven thematic areas. Finally, this review stresses that future research should consider developing a converging theoretical framework that would enable concrete monitoring and support for self‐regulation and socially shared regulation of learning. Our findings set a baseline to support the adoption and proliferation of adaptive learning technology within self‐regulated learning research and development. Practitioner notesWhat is already known about this topic By providing personalized and learner‐centric adaptive learning environments (ADLEs), adaptive learning technology can support and foster self‐regulated learning (SRL) practices.It is possible to create a more student‐centred and effective learning environment by combining adaptive learning and collaborative learning.Socially shared regulatory activities can involve planning, monitoring, controlling and reflecting on a group's learning processes.What this paper adds Provides a systematic literature review of empirical evidence on ADLEs, SRL and socially shared regulation of learning (SSRL) in collaborative contexts.Summarizes the insights on (S)SRL through ADLEs in collaborative learning.Identifies challenges and opportunities for ADLEs to support (S)SRL in collaborative learning.Implications for practice and/or policy Learning analytics and educational technology researchers will be able to use the systematic review as a guide for future research.Learning analytics and educational technology practitioners will be able to use the systematic review as a summary of the field's current state. [ABSTRACT FROM AUTHOR]

Educational podcasts have become an increasingly prevalent media used to disseminate profession‐specific information through easily accessible means. Despite the potential of educational podcasts as convenient and effective medium, there is a dearth of literature dedicated to the topic. Thus, using the Uses and Gratification framework, the psychometric properties of the Educational Podcasts Motivation Scale were examined, as well as the motivational factors that influence intention to listen to educational podcasts and recommend podcasts to others were explored. A sample of individuals in the field of education (n = 606), such as in‐service K‐12 teachers and higher education professors, were recruited for this study. This sample were randomly divided, and an exploratory factor analysis (EFA) was conducted with the first set (n = 312) to identify underlying constructs, and confirmatory factor analysis (CFA) and structural equation modelling (SEM) were employed with the second set (n = 294). The scale demonstrated strong psychometric properties and five distinct motivational factors were identified: Information Gathering, Flexibility in Use, Social Interaction, Entertainment, and Professional Encouragement. Several motivational factors had significant associations with the constructs of "intention" and "word‐of‐mouth". This paper demonstrates both the unique motivational factors related to listening to educational podcasts and the motivational factors that overlap with other forms of media. Further examination of the underlying motivations to listen to educational podcasts is warranted. Practitioner notesWhat is already known about this topic Educational podcasts have become an increasingly prevalent media used to disseminate information to specific professions and fields that provide current practices and research information through easily accessible means.Educational podcasts have been found to be an effective tool to improve self‐efficacy and knowledge around topics with educators and college students, as well as a means to develop communities of practice where educators share knowledge and experiences.Results of studies using the uses and gratifications framework to examine the gratifications for listening to podcasts have found an array of overlapping, and sometimes conflicting, gratifications from the use of podcasts. Those most often identified include entertainment, multitasking and convenience, social interaction, escapism and educational purposes.What this paper adds This paper outlined the development of the Educational Podcasts Motivation Scale and used an exploratory factor analysis, confirmatory factor analysis and structural equation modelling to demonstrate its strong psychometric properties.Five distinct motivational factors for why educators engage with educational podcasts were identified: (a) Information Gathering, (b) Flexibility in Use, (c) Social Interaction, (d) Entertainment and (e) Professional Encouragement.This paper identifies that educators are often most motivated to listen to educational podcasts due to constructs such as social interaction, flexibility in use and information gathering.Implications for practice and/or policy The findings in this paper demonstrate the perceived benefits and uses of educational podcasts as a learning tool, further establishing educational podcasts as a useful tool that should be incorporated into learning environments.The findings in this paper indicate that those embedding educational podcasts within learning activities and professional development should consider how to emphasise the flexibility, social interactions and learning aspects of these tools to promote the attractive features of this tool.Although this study sheds light on the reasons those in the field of education use this medium, additional research is needed to explore how and why these individuals engage with educational podcasts. [ABSTRACT FROM AUTHOR]

Training to run is not straightforward since without proper personalised supervision and planning, people will not improve their performance and will increase the risk of injuries. This study aims to identify the different factors that influence running training programmes, examining the benefits, challenges or limitations of personalised plans. Moreover, this study explores how multimodal, immersive and artificial intelligence technologies can support personalised training. We conducted an exploratory sequential mixed research consisting of interviews with 11 running coaches from different countries and a survey of 12 running coaches. Based on the interviews and survey analysis, we identified and extracted relevant factors of the training process. We identified four relevant aspects for running training: physical, technical, mental and body awareness. Using these aspects as a reference, we derived a framework using a bottom‐up approach. This framework proposes multimodal, immersive and artificial intelligence technologies to facilitate personalised running training. It also allows coaches to personally guide their athletes on each aspect. Practitioner notesWhat is already known about this topic Running is a popular sport that provides health benefits and is practised by many people around the world.Training is a process that enables athletes to improve their development in various aspects of their sport; in the case of running, it helps them to increase their speed and endurance.Personalised training supports the needs and abilities of athletes, by helping them to achieve their potential through individualised activities or programmes.Sports science research indicates that personalised training can be improved by applying technology to tackle its challenges and limitations.What this paper adds We show that personalising the training requires not only focusing on the runners' physical condition but also on their mental, technical and body awareness aspects, where each of them has a different adaptation to training.We show that multimodal and immersive technologies offer suitable and portable ways to measure and target the mental and body awareness aspects during running training.Implications for practice and/or policy This paper presents a list of factors, measures and devices that coaches can use to plan and design their training sessions in a more personalised manner.This study can serve as a foundation for future research that aims to identify and target the various factors that influence the learning and training of sports. [ABSTRACT FROM AUTHOR]

The paper argues that learning analytics as a research field can benefit from a theory‐informed shared language to describe sensemaking of learning and teaching data. To make the case for such shared language, first, I critically review prominent sensemaking theories to then demonstrate how studies in learning analytics do not use coherent descriptions of sensemaking, eclectically combining the paradigms that have underlying differences. I then propose a conceptualization of sensemaking that overcomes the differences between these theories and explains how the concepts of activity system, the definition of the situation and affordances can be used to capture individual differences in sensemaking. The paper concludes with a preliminary framework and examples demonstrating its utility in raising new theoretical questions, informing design principles and providing shared language for researchers in learning analytics.Practitioner notesWhat is already known about this topicSensemaking happens when individuals try to explain unknown situations.Learning analytics uses sensemaking as a lens to understand dashboard use.Systematic analysis of sensemaking is essential for learning analytics.What this paper addsThe paper notes that noticing and perceiving are commonly examined in learning analytics on dashboard use.The paper suggests a revision of fundamental assumptions in sensemaking.A paper proposes a toy model of sensemaking that includes operationalization of the definition of the situation, activity where sensemaking happens and processes of noticing and perceiving affordances.Implications for practice and/or policyLearning analytics must examine sensemaking of data about teaching and learning in a systematic manner.Internal perceptions of the social environment and activity that are informed by the data need to be considered in evaluating dashboard use. [ABSTRACT FROM AUTHOR]

Previous research showed that the parents acknowledged the technology's benefits for their young children's learning, however, they are still worried about the extended screen time, lack of physical activity and lack of social interactions. To address these concerns, we developed Kid Space to enable pedagogically appropriate technology use for children in early childhood education by combining various sensing technologies with a multi‐modal conversational artificial intelligence system that can interact with children, understand individual progress and provide personalised learning experiences. To understand the impact of Kid Space on the parents' initial concerns about technology use by their young children, we conducted a multi‐method user study: (1) a quasi‐experimental design and (2) formative research method using an exploratory case study with a set of children and their parents experiencing Kid Space in their homes. The results show that after experiencing Kid Space with their children, the parents felt significantly less concerned about screen time, social interactions and physical activity and reported positive perceptions towards pedagogical value of Kid Space. Detailed analysis on the multi‐modal data quantitatively and qualitatively validated why Kid Space alleviated these concerns. Future research is needed to validate long‐term educational value of Kid Space and generate insights for improvement for next iterations. Practitioner notesWhat is already known about this topic Play‐based learning is critical for young children's education, but digital games create major concerns around extended screen time, lack of physical activity and lack of social interactions.Blending digital and physical spaces could support pedagogically appropriate technology use for young children. Towards this end, there are some exemplary studies in the state–of‐the‐art reporting positive educational outcomes as an effect of utilising such spaces. However, none of these studies supported children's most natural mode of communication in their interactions with the systems—speaking.Pedagogical conversational agents (PCAs) are promising, but they are tricky when it comes to young children's speech because of unique technical challenges resulted from how children use language and communicate with digital systems.What this paper adds To our best knowledge, Kid Space is one of the earliest implementations of a PCA with a multi‐modal artificial intelligence (AI) system utilising physical and digital learning manipulatives for maths learning with a focus on early childhood education. The key contributions of this paper are (1) the design and development of an end‐to‐end multi‐modal system enabling Wizard‐of‐Oz experimentation for initial evaluations with users, (2) the creation of a multi‐modal, in‐the‐wild labelled dataset with children–agent, children–parent and children–physical/digital space interactions enabling advancements for AI components for later evaluations with users and (3) the generation of rich insights from an initial research study on user perceptions and engagement as well as actionable findings to improve Kid Space experiences for next iterations and inform key design features for similar systems.Implications for practice and/or policy The results of the study implied a set of areas for improvement—or design features—for Kid Space and other similar pedagogical conversational systems developed for children's home usages: (1) easier setup and usage with optimised setup size addressing diverse space limitations at homes, (2) minimised latency between Oscar (the conversational pedagogical agent) and child interactions (eg, adding multimodal dialogue system to reduce the need for a human wizard), (3) more advanced personalisation, social (including more verbal interactions) and pedagogical skills for Oscar with increased contextual awareness (eg, sending children's engagement), (4) scalability and higher visual quality of content with diverse games and learning outcomes, (5) parental control features over Kid Space platform and Oscar (eg, time limit, content, etc.) and (6) accessibility features (eg, captions turned on for multilingual children) and support for neurodiversity. [ABSTRACT FROM AUTHOR]

This study investigated the seamless mobile learning practices of UK government workers at various life stages, to understand how context impacted decisions about how, when and where learning was undertaken. Following Hedegaard, the context was understood as involving settings embedded within institutions. Drawing on analysis of data from public domain blogs and reports and anonymised trace data showing e‐learning visits via a mobile device, a picture of institutional practice and values was developed. Against this backdrop, a survey of 50 individuals followed by semi‐structured interviews provided information about seamless mobile learning projects. Mobile learning was often fragmented and ad hoc, rather than part of a longer, seamless learning project. A distinction between just‐in‐time learning and just‐in‐case learning was apparent, with the latter often postponed. For mobile workers, mobile learning focused on current work setting, whereas workers who could work in many interchangeable settings might move to somewhere they could concentrate. Mobile learning was sometimes motivated by a sense of a lack of time and a need to stay 'on top of things' as much as by interest in a topic. Sustained seamless mobile learning projects occurred if there was institutional support for learning that was also of individual interest and if learners had the ability to orchestrate their learning. Learners reported these seamless mobile learning projects to be enjoyable and compelling. This paper contributes to the evidence of seamless mobile learning practice over the life course and illustrates the value of considering an individual's relation to various institutions in conceptualisations of seamless mobile learning. It also offers pointers for the future design of seamless mobile learning tools including a need to offer learners the opportunity to sometimes separate ongoing learning which is related to distinct institutions.Practitioner notesWhat is already known about this topicMobile devices accompany their owners across settings that were previously considered separate, such as work, college and households.This has the potential to impact work/home and other boundaries.From a pedagogical perspective, mobile devices may support seamless learning, in which experiences across distinct settings result in a holistic and unified understanding.What this paper addsIt introduces the concept of the institution to conceptions of seamless learning.It illustrates the ways in which different institutions (workplaces or educational institutions) can shape individual experiences and decisions about when and where to learn.It provides evidence that some working adults engage in seamless learning projects and describe this as compelling and enjoyable, but that others prefer to separate distinct life spheres.Implications for practice and/or policyThere may be value in institutions and designers supporting people who want to engage in seamless mobile learning.However, it is important to be aware that not everyone wants to engage in seamless learning.Seamless learning is more likely to occur when individual and institutional priorities are aligned across several institutions, so there will be challenges for a single institution seeking to promote it. [ABSTRACT FROM AUTHOR]

Multimodal learning analytics (MMLA) research has made significant progress in modelling collaboration quality for the purpose of understanding collaboration behaviour and building automated collaboration estimation models. Deploying these automated models in authentic classroom scenarios, however, remains a challenge. This paper presents findings from an evaluation of collaboration quality estimation models. We collected audio, video and log data from two different Estonian schools. These data were used in different combinations to build collaboration estimation models and then assessed across different subjects, different types of activities (collaborative‐writing, group‐discussion) and different schools. Our results suggest that the automated collaboration model can generalize to the context of different schools but with a 25% degradation in balanced accuracy (from 82% to 57%). Moreover, the results also indicate that multimodality brings more performance improvement in the case of group‐discussion‐based activities than collaborative‐writing‐based activities. Further, our results suggest that the video data could be an alternative for understanding collaboration in authentic settings where higher‐quality audio data cannot be collected due to contextual factors. The findings have implications for building automated collaboration estimation systems to assist teachers with monitoring their collaborative classrooms. Practitioners notesWhat is already known about this topicMultimodal learning analytics researchers have established several features as potential indicators for collaboration quality, e.g., speaking time or joint visual attention.The current state of the art has shown the feasibility of building automated collaboration quality models.Recent research has provided preliminary evidence of the generalizability of developed automated models across contexts different in terms of given task and subject.What does this paper addThis paper offers collaboration indicators for different types of collaborative learning activities in authentic classroom settings.The paper includes a systematic investigation into collaboration quality automated model's generalizability across different tasks, types of tasks and schools.This paper also offers a comparison between different modalities' potential to estimate collaboration quality in authentic settings.Implications for practiceThe findings inform the development of automated collaboration monitoring systems for authentic classroom settings.This paper provides evidence on across‐school generalizability capabilities of collaboration quality estimation models. [ABSTRACT FROM AUTHOR]

This research employs the fuzzy‐set qualitative comparative analysis (fsQCA) method to investigate the configurations of multiple factors influencing scientific concept learning, including augmented reality (AR) technology, the concept map (CM) strategy and individual differences (eg, prior knowledge, experience and attitudes). A quasi‐experiment was conducted with 194 seventh‐grade students divided into four groups: AR and CM (N = 52), AR and non‐CM (N = 51), non‐AR and CM (N = 40), non‐AR and non‐CM (N = 51). These students participated in a science lesson on ‘The structure of peach blossom’. This study represents students' science learning outcomes by measuring their academic performance and cognitive load. The fsQCA results reveal that: (1) factors influencing students' academic performance and cognitive load are interdependent, and a single factor cannot constitute a necessary condition for learning outcomes; (2) multiple pathways can lead to the same learning outcome, challenging the notion of a singular best path derived from traditional analysis methods; (3) the configurations of good and poor learning outcomes exhibit asymmetry. For example, high prior knowledge exists in both configurations leading to good and poor learning outcomes, depending on how other conditions are combined. Practitioner notes What is already known about this topic Augmented reality proves to be a useful technological tool for improving science learning. The concept map can guide students to describe the relationships between concepts and make a connection between new knowledge and existing knowledge structures. Individual differences have been emphasized as essential external factors in controlling the effectiveness of learning. What this paper adds This study innovatively employed the fsQCA analysis method to reveal the complex phenomenon of the scientific concept learning process at a fine‐grained level. This study discussed how individual differences interact with AR and concept map strategy to influence scientific concept learning. Implications for practice and/or policy No single factor present or absent is necessary for learning outcomes, but the combinations of AR and concept map strategy always obtain satisfactory learning outcomes. There are multiple pathways to achieving good learning outcomes rather than a single optimal solution. The implementation of educational interventions should fully consider students' individual differences, such as prior knowledge, experience and attitudes. What is already known about this topic Augmented reality proves to be a useful technological tool for improving science learning. The concept map can guide students to describe the relationships between concepts and make a connection between new knowledge and existing knowledge structures. Individual differences have been emphasized as essential external factors in controlling the effectiveness of learning. What this paper adds This study innovatively employed the fsQCA analysis method to reveal the complex phenomenon of the scientific concept learning process at a fine‐grained level. This study discussed how individual differences interact with AR and concept map strategy to influence scientific concept learning. Implications for practice and/or policy No single factor present or absent is necessary for learning outcomes, but the combinations of AR and concept map strategy always obtain satisfactory learning outcomes. There are multiple pathways to achieving good learning outcomes rather than a single optimal solution. The implementation of educational interventions should fully consider students' individual differences, such as prior knowledge, experience and attitudes. [ABSTRACT FROM AUTHOR]

Multimodal learning analytics (MMLA) offers the potential to provide evidence‐based insights into complex learning phenomena such as collaborative learning. Yet, few MMLA applications have closed the learning analytics loop by being evaluated in real‐world educational settings. This study evaluates the effectiveness of an MMLA solution in enhancing feedback and reflection within a complex and highly dynamic collaborative learning environment. A two‐year longitudinal study was conducted with 399 students and 17 teachers, utilising an MMLA system in reflective debriefings in the context of healthcare education. We analysed the survey data of 74 students and 11 teachers regarding their perceptions of the MMLA system. We applied the Evaluation Framework for Learning Analytics, augmented by complexity, accuracy and trust measures, to assess both teachers' and students' perspectives. The findings illustrated that teachers and students both had generally positive perceptions of the MMLA solution. Teachers found the MMLA solution helpful in facilitating feedback provision and reflection during debriefing sessions. Similarly, students found the MMLA solution effective in providing clarity on the data collected, stimulating reflection on their learning behaviours, and prompting considerations for adaptation in their learning behaviours. However, the complexity of the MMLA solution and the need for qualitative measures of communication emerged as areas for improvement. Additionally, the study highlighted the importance of data accuracy, transparency, and privacy protection to maintain user trust. The findings provide valuable contributions to advancing our understanding of the use of MMLA in supporting feedback and reflection practices in intricate collaborative learning while identifying avenues for further research and improvement. We also provided several insights and practical recommendations for successful MMLA implementation in authentic learning contexts. Practitioner notes What is currently known about this topic Multimodal learning analytics (MMLA) seeks to generate data‐informed insights about learners' metacognitive and emotional states as well as their learning behaviours, by utilising intricate physical and physiological signals. MMLA has not only pioneered novel data analytic methods but also aspired to complete the learning analytics loop by crafting innovative, tangible solutions that relay these insights to the concerned stakeholders. A prominent direction within MMLA research has been the formulation of tools to support feedback and reflection in collaborative learning scenarios, given MMLA's capacity to discern intricate and dynamic learning behaviours. What this paper adds Teachers' and students' positive perceptions of an MMLA implementation in stimulating considerations of adaptations in their pedagogical practices and learning behaviours, respectively. Empirical evidence supporting the potential of MMLA in assisting teachers to facilitate students' reflective practices during intricate collaborative learning scenarios. The importance of addressing issues related to design complexity, interpretability for users with disabilities, aggregated data representation, and concerns related to trust for building a practical MMLA solution in real learning settings. Implications for practice and/or policy The MMLA solution can provide teachers with a comprehensive view of student performance, illuminate areas for improvement, and confirm learning scenario outcomes. The MMLA solution can stimulate students' reflections on their learning behaviours and promote considerations of adaptation in their learning behaviours. Providing clear explanations and guidance on how to interpret analytics, as well as addressing concerns related to data completeness and representation, are essential to maximising utility. What is currently known about this topic Multimodal learning analytics (MMLA) seeks to generate data‐informed insights about learners' metacognitive and emotional states as well as their learning behaviours, by utilising intricate physical and physiological signals. MMLA has not only pioneered novel data analytic methods but also aspired to complete the learning analytics loop by crafting innovative, tangible solutions that relay these insights to the concerned stakeholders. A prominent direction within MMLA research has been the formulation of tools to support feedback and reflection in collaborative learning scenarios, given MMLA's capacity to discern intricate and dynamic learning behaviours. What this paper adds Teachers' and students' positive perceptions of an MMLA implementation in stimulating considerations of adaptations in their pedagogical practices and learning behaviours, respectively. Empirical evidence supporting the potential of MMLA in assisting teachers to facilitate students' reflective practices during intricate collaborative learning scenarios. The importance of addressing issues related to design complexity, interpretability for users with disabilities, aggregated data representation, and concerns related to trust for building a practical MMLA solution in real learning settings. Implications for practice and/or policy The MMLA solution can provide teachers with a comprehensive view of student performance, illuminate areas for improvement, and confirm learning scenario outcomes. The MMLA solution can stimulate students' reflections on their learning behaviours and promote considerations of adaptation in their learning behaviours. Providing clear explanations and guidance on how to interpret analytics, as well as addressing concerns related to data completeness and representation, are essential to maximising utility. [ABSTRACT FROM AUTHOR]

Teachers who know what, how and why to teach are essential for successful student learning. However, many preservice teachers (PSTs) lack teaching experience and the ability to integrate theory and practice. To help bridge this gap, this study employed a learning‐by‐design project approach in which 22 Korean PSTs developed lesson plans for middle school English classes, constructed virtual classrooms in the metaverse based on their English lesson plans, and conducted microteaching in the virtual classrooms. The study used a qualitative research method and focused on an emic perspective with multiple data sets, including the PSTs' reflection papers and post‐interviews as primary data, and their lesson plans, virtual classrooms and recordings of microteaching as secondary data. The results showed that the project supported learning by design, and that it also helped PSTs understand learners and learning, redefine the teacher's role as a designer and facilitator, connect theories to practice and improve their teaching skills. The findings can be used as a reference for future teacher training. Practitioner notes What is already known about this topic Teachers' content, pedagogical and technological knowledge and skills are essential attributes for effective performance. Preservice teachers (PSTs) have difficulty transferring their knowledge to real classrooms because their knowledge often focuses on the ‘know‐what’ of teaching, but not on the ‘know‐how’. Microteaching in virtual environments helps PSTs connect knowledge and practice and prepare for real classroom situations. What this paper adds The study applied a learning‐by‐design approach to preservice teachers' microteaching to help them connect their pedagogical knowledge to classroom practice. The study focused on describing how the PSTs' virtual classroom design influenced the way they planned and implemented their microteaching. Implications for practice and/or policy Teacher educators can incorporate the design‐based approach into their teacher training modules to help teachers understand learner needs when planning and implementing English lessons. Teachers can develop technological literacy and positive attitudes about using technology in their classrooms. What is already known about this topic Teachers' content, pedagogical and technological knowledge and skills are essential attributes for effective performance. Preservice teachers (PSTs) have difficulty transferring their knowledge to real classrooms because their knowledge often focuses on the ‘know‐what’ of teaching, but not on the ‘know‐how’. Microteaching in virtual environments helps PSTs connect knowledge and practice and prepare for real classroom situations. What this paper adds The study applied a learning‐by‐design approach to preservice teachers' microteaching to help them connect their pedagogical knowledge to classroom practice. The study focused on describing how the PSTs' virtual classroom design influenced the way they planned and implemented their microteaching. Implications for practice and/or policy Teacher educators can incorporate the design‐based approach into their teacher training modules to help teachers understand learner needs when planning and implementing English lessons. Teachers can develop technological literacy and positive attitudes about using technology in their classrooms. [ABSTRACT FROM AUTHOR]

Video‐based learning (VBL) is popular, yet students tend to learn video material passively. Instilling teaching expectancy is a strategy to promote active processing by learners, but it is unclear how effective it will be in improving VBL. This study examined the role of teaching expectancy on VBL by comparing the learning outcomes and metacognitive monitoring of 94 learners with different expectancies (teaching, test or no expectancy). Results showed that the teaching expectancy group had better learning outcomes and no significant difference in the metacognitive monitoring of three groups. We further explored the visual behaviour patterns of learners with different expectancies by using the indicator of eye‐movement synchronization. It was found that synchronization was significantly lower in both the teaching and test expectancy groups than in the no expectancy group, and the test expectancy group was significantly lower than the teaching expectancy group. This result suggests that both teaching and test expectancy enhance the active processing of VBL. However, by sliding window analysis, we found that the teaching expectancy group used a flexible and planned attention allocation. Our findings confirmed the effectiveness of teaching expectancy in VBL. Also, this study provided evidence for the applicability of eye‐tracking techniques to assess VBL. Practitioner notes What is already known about this topic Video‐based learning has become a popular way, yet students tend to learn video material passively. When students learn with teaching expectancy, they are more likely to engage in deep processing, which has been proven in static multimedia learning. Individuals show high eye‐movement synchronization when watching the same video, and this synchronization may be reduced when they engage in top‐down processing. What this paper adds Teaching expectancy improves learning performance in Video‐based learning. Teaching expectancy enhances active cognitive processing in Video‐based learning. During the video viewing, learners with teaching expectancy not only followed the instructor's explanations but also engaged in active top‐down processing, demonstrating flexible and planned attention allocation. Implications for practice and/or policy Utilizing teaching as an intention can serve as an effective learning strategy for Video‐based learning. The use of eye‐movement intersubject correlation to analyse visual behaviour patterns provides a new way to explore how people learn from dynamic multimedia materials. What is already known about this topic Video‐based learning has become a popular way, yet students tend to learn video material passively. When students learn with teaching expectancy, they are more likely to engage in deep processing, which has been proven in static multimedia learning. Individuals show high eye‐movement synchronization when watching the same video, and this synchronization may be reduced when they engage in top‐down processing. What this paper adds Teaching expectancy improves learning performance in Video‐based learning. Teaching expectancy enhances active cognitive processing in Video‐based learning. During the video viewing, learners with teaching expectancy not only followed the instructor's explanations but also engaged in active top‐down processing, demonstrating flexible and planned attention allocation. Implications for practice and/or policy Utilizing teaching as an intention can serve as an effective learning strategy for Video‐based learning. The use of eye‐movement intersubject correlation to analyse visual behaviour patterns provides a new way to explore how people learn from dynamic multimedia materials. [ABSTRACT FROM AUTHOR]

This study investigates the validity and reliability of generative large language models (LLMs), specifically ChatGPT and Google's Bard, in grading student essays in higher education based on an analytical grading rubric. A total of 15 experienced English as a foreign language (EFL) instructors and two LLMs were asked to evaluate three student essays of varying quality. The grading scale comprised five domains: grammar, content, organization, style & expression and mechanics. The results revealed that fine‐tuned ChatGPT model demonstrated a very high level of reliability with an intraclass correlation (ICC) score of 0.972, Default ChatGPT model exhibited an ICC score of 0.947 and Bard showed a substantial level of reliability with an ICC score of 0.919. Additionally, a significant overlap was observed in certain domains when comparing the grades assigned by LLMs and human raters. In conclusion, the findings suggest that while LLMs demonstrated a notable consistency and potential for grading competency, further fine‐tuning and adjustment are needed for a more nuanced understanding of non‐objective essay criteria. The study not only offers insights into the potential use of LLMs in grading student essays but also highlights the need for continued development and research. Practitioner notes What is already known about this topic Large language models (LLMs), such as OpenAI's ChatGPT and Google's Bard, are known for their ability to generate text that mimics human‐like conversation and writing. LLMs can perform various tasks, including essay grading. Intraclass correlation (ICC) is a statistical measure used to assess the reliability of ratings given by different raters (in this case, EFL instructors and LLMs). What this paper adds The study makes a unique contribution by directly comparing the grading performance of expert EFL instructors with two LLMs—ChatGPT and Bard—using an analytical grading scale. It provides robust empirical evidence showing high reliability of LLMs in grading essays, supported by high ICC scores. It specifically highlights that the overall efficacy of LLMs extends to certain domains of essay grading. Implications for practice and/or policy The findings open up potential new avenues for utilizing LLMs in academic settings, particularly for grading student essays, thereby possibly alleviating workload of educators. The paper's insistence on the need for further fine‐tuning of LLMs underlines the continual interplay between technological advancement and its practical applications. The results lay down a footprint for future research in advancing the use of AI in essay grading. What is already known about this topic Large language models (LLMs), such as OpenAI's ChatGPT and Google's Bard, are known for their ability to generate text that mimics human‐like conversation and writing. LLMs can perform various tasks, including essay grading. Intraclass correlation (ICC) is a statistical measure used to assess the reliability of ratings given by different raters (in this case, EFL instructors and LLMs). What this paper adds The study makes a unique contribution by directly comparing the grading performance of expert EFL instructors with two LLMs—ChatGPT and Bard—using an analytical grading scale. It provides robust empirical evidence showing high reliability of LLMs in grading essays, supported by high ICC scores. It specifically highlights that the overall efficacy of LLMs extends to certain domains of essay grading. Implications for practice and/or policyThe findings open up potential new avenues for utilizing LLMs in academic settings, particularly for grading student essays, thereby possibly alleviating workload of educators.The paper's insistence on the need for further fine‐tuning of LLMs underlines the continual interplay between technological advancement and its practical applications.The results lay down a footprint for future research in advancing the use of AI in essay grading. [ABSTRACT FROM AUTHOR]

Dementia patients may have language barriers and decreased comprehension ability. Their family caregivers can feel frustrated when communicating with them. Poor communication hinders family caregivers from obtaining accurate health information about patients, and may also increase their emotional burden, affecting patient care quality. The present study developed a virtual reality‐based simulated communication training (VRSCT) system and applied it to a training course for family caregivers of dementia patients. It allowed family caregivers to simulate real‐world situations in a VR environment, experience the daily communication barriers and stress with dementia patients, and apply their acquired knowledge and skills to solve related problems. This study used a randomised control experimental design with mixed analysis methods. A total of 63 family caregivers were recruited and randomly divided into the experimental group (N = 32) learning with the VRSCT system to interact with virtual dementia patients and practice communication skills, and the control group (N = 31) using the traditional role‐playing method for practice. Quantitative data were analysed to determine participants' knowledge of dementia care, attitudes, communication confidence and skills. In addition, the qualitative method was used to analyse the participants' discussion records. The results showed that by using the VRSCT approach, participants significantly improved their knowledge of dementia care, attitudes, communication confidence and communication skills compared to the control group. In addition, participants reported that through the real‐time feedback of the VRSCT system, they could recognise their previous incorrect communication approach. As a result, they adjusted their communication strategies and increased their self‐confidence. Practitioner notes What is already known about this topic Situational simulation helps learners improve their communication skills in a safe environment. Virtual reality (VR) creates a realistic, highly interactive learning environment, allowing users to be deeply immersed in the learning experience. What this paper adds This study proposed a VR‐based simulated communication training (VRSCT) approach; moreover, seven dementia cases of different degrees of severity were designed in the VR system to enable family members to experience possible challenges of taking care of dementia patients they might encounter in their daily lives. Each case in the VRSCT system has its unique symptoms and communication barriers. The learner in the story plays a caregiver, experiencing and solving the problems and challenges posed by the system. The experimental results show that the proposed method improves learners' knowledge, attitudes, communication confidence, and communication skills related to dementia care. Implications for practice and/or policy Utilising VR training can amplify awareness and secure enhanced social support for dementia‐related challenges. Using VRSCT, as governments and institutions recognise the effectiveness of VR training, they will provide more resources and promote its widespread application. What is already known about this topic Situational simulation helps learners improve their communication skills in a safe environment. Virtual reality (VR) creates a realistic, highly interactive learning environment, allowing users to be deeply immersed in the learning experience. What this paper adds This study proposed a VR‐based simulated communication training (VRSCT) approach; moreover, seven dementia cases of different degrees of severity were designed in the VR system to enable family members to experience possible challenges of taking care of dementia patients they might encounter in their daily lives. Each case in the VRSCT system has its unique symptoms and communication barriers. The learner in the story plays a caregiver, experiencing and solving the problems and challenges posed by the system. The experimental results show that the proposed method improves learners' knowledge, attitudes, communication confidence, and communication skills related to dementia care. Implications for practice and/or policy Utilising VR training can amplify awareness and secure enhanced social support for dementia‐related challenges. Using VRSCT, as governments and institutions recognise the effectiveness of VR training, they will provide more resources and promote its widespread application. [ABSTRACT FROM AUTHOR]

Universities, significantly impacted by the shift to online learning during pandemic, must critically evaluate their teaching methods and outcomes to enhance performance in the post‐pandemic era. However, there has been a limited examination of whether students achieved comparable levels in cognition and social interaction during the pandemic compared to traditional face‐to‐face learning. Addressing this gap, this exploratory study utilized a quasi‐experimental design to analyse and compare the learning performance and outcomes of two cohorts of students (totalling 45) in a 12‐week university course delivered through the computer‐supported collaborative learning (CSCL) approach, both during and after the pandemic. Employing quantitative analysis and lag sequential analysis, the study examined students' behaviours, similarities and differences in performance within CSCL environments under two distinct social situations. Results indicated that students engaged in complete online learning with CSCL and those in face‐to‐face teaching with CSCL achieved similar levels of conceptual understanding. Additionally, a comparable distribution pattern of learning behaviours was observed. However, significant differences in behaviour sequences emerged between the two implementations, with students exhibiting a higher level of engagement in CSCL activities during the post‐pandemic period. These findings inform the design of CSCL environments should integrate student‐centred activities and include guiding scripts, prompts and scaffoldings in navigating learning endeavours effectively. Practitioner notes What is already known about this topic The CSCL environment could facilitate teacher‐student and student–student interaction in learning activities. Studies have been conducted on the impact of scripts and prompts on students' cognition and social interaction in CSCL environment. There is a crucial need for conducting more in‐depth data analysis to comprehensively explore the CSCL process within university settings. What this paper adds A well‐designed CSCL environment, coupled with effective instructional strategies, exhibits resilience, sustaining its beneficial effects on students' academic performance and interaction. Both cohorts demonstrated a proclivity for engaging in repetitive behaviours, particularly focused on reviewing and reading activities. The latter cohort displayed a preference for individual tasks over collaborative efforts, showcasing a relatively higher frequency of individual work as opposed to group activities. Notably absent in both groups were crucial behavioural sequences, namely VR‐IA and VC‐IA, underscoring potential areas for CSCL improvement. Implications for practice and/or policy In the CSCL environment, a variety of activities rooted in student‐centred pedagogy (ie, self‐regulated learning, inquiry‐based learning and peer feedback) should be seamlessly integrated. It is recommended to furnish students with scripts, prompts and scaffoldings to bolster their navigation through collaborative and independent learning endeavours within CSCL environment. Students are encouraged to bridge their newly acquired knowledge with their existing understanding, for enhancing engagement and promoting deeper comprehension. What is already known about this topic The CSCL environment could facilitate teacher‐student and student–student interaction in learning activities. Studies have been conducted on the impact of scripts and prompts on students' cognition and social interaction in CSCL environment. There is a crucial need for conducting more in‐depth data analysis to comprehensively explore the CSCL process within university settings. What this paper adds A well‐designed CSCL environment, coupled with effective instructional strategies, exhibits resilience, sustaining its beneficial effects on students' academic performance and interaction. Both cohorts demonstrated a proclivity for engaging in repetitive behaviours, particularly focused on reviewing and reading activities. The latter cohort displayed a preference for individual tasks over collaborative efforts, showcasing a relatively higher frequency of individual work as opposed to group activities. Notably absent in both groups were crucial behavioural sequences, namely VR‐IA and VC‐IA, underscoring potential areas for CSCL improvement. Implications for practice and/or policy In the CSCL environment, a variety of activities rooted in student‐centred pedagogy (ie, self‐regulated learning, inquiry‐based learning and peer feedback) should be seamlessly integrated. It is recommended to furnish students with scripts, prompts and scaffoldings to bolster their navigation through collaborative and independent learning endeavours within CSCL environment. Students are encouraged to bridge their newly acquired knowledge with their existing understanding, for enhancing engagement and promoting deeper comprehension. [ABSTRACT FROM AUTHOR]

Authentic dialogue demands that we respond, interpret and sometimes disagree with others' ideas—a key component of participation in a democratic society. Yet the sharing and uptake of different ideas can be hampered by traditional online platforms which divide students into isolated threads. To tackle this issue, we introduce two novel online forums designed to foster engagement and idea exchange: a linear chat, akin to SMS, and a collaborative writing forum we call CREW. Seventy‐three graduate students, divided into 18 small groups, tested these forums. We used discourse analysis to measure idea uptake and other dialogic features. From this analysis, seven discussions emerged as particularly interactive and engaging, exhibiting a high uptake‐to‐turn ratio. We noticed linear chat encouraged a high proportion of uptake, but also produced ‘tangles’—breaks in related post chains. CREW discussions sparked similar engagement but resolved most tangles since they required a collaborative written response. This study offers fresh insights in both research and teaching for improving online discussions. Practitioner notes What is already known about this topic A vital practice for scholarly dialogue and democratic discourse is uptake: building on what others have written or said. Instead of encouraging uptake of others' words and ideas, typical online discussions in Learning Management Systems (LMSs) can inadvertently isolate students in separate threads. What this paper adds We introduce and analyse two new, innovative types of online discussions that may encourage more uptake of others' words and ideas. To eliminate isolation and encourage uptake, a linear chat forum makes all posts visible, but may produce interruptions, or ‘tangles’. A forum that includes collaborative responsive writing requires participants to converge on a collective response, encouraging dialogue and overcoming tangles. Implications for practice/policy Teachers and other stakeholders might consider how discussion forum designs in LMSs can support or limit authentic dialogue. Practitioners might consider how to incorporate deliberation about a shared focus into online discussions. Instructors might avoid tangles by aligning assignment purposes with dialogic principles: posing authentic questions that invite multiple interpretations and require uptake of others' responses. What is already known about this topic A vital practice for scholarly dialogue and democratic discourse is uptake: building on what others have written or said. Instead of encouraging uptake of others' words and ideas, typical online discussions in Learning Management Systems (LMSs) can inadvertently isolate students in separate threads. What this paper adds We introduce and analyse two new, innovative types of online discussions that may encourage more uptake of others' words and ideas. To eliminate isolation and encourage uptake, a linear chat forum makes all posts visible, but may produce interruptions, or ‘tangles’. A forum that includes collaborative responsive writing requires participants to converge on a collective response, encouraging dialogue and overcoming tangles. Implications for practice/policy Teachers and other stakeholders might consider how discussion forum designs in LMSs can support or limit authentic dialogue. Practitioners might consider how to incorporate deliberation about a shared focus into online discussions. Instructors might avoid tangles by aligning assignment purposes with dialogic principles: posing authentic questions that invite multiple interpretations and require uptake of others' responses. [ABSTRACT FROM AUTHOR]

The greater the proliferation of AI in educational contexts, the more important it becomes to ensure that AI adheres to the equity and inclusion values of an educational system or institution. Given that modern AI is based on historic datasets, mitigating historic biases with respect to protected classes (ie, fairndess) is an important component of this value alignment. Although extensive research has been done on AI fairness in education, there has been a lack of guidance for practitioners, which could enhance the practical uptake of these methods. In this work, we present a practitioner‐oriented, step‐by‐step framework, based on findings from the field, to implement AI fairness techniques. We also present an empirical case study that applies this framework in the context of a grade prediction task using data from a large public university. Our novel findings from the case study and extended analyses underscore the importance of incorporating intersectionality (such as race and gender) as central equity and inclusion institution values. Moreover, our research demonstrates the effectiveness of bias mitigation techniques, like adversarial learning, in enhancing fairness, particularly for intersectional categories like race–gender and race–income. Practitioner notes What is already known about this topic AI‐powered Educational Decision Support Systems (EDSS) are increasingly used in various educational contexts, such as course selection, admissions, scholarship allocation and identifying at‐risk students. There are known challenges with AI in education, particularly around the reinforcement of existing biases, leading to unfair outcomes. The machine learning community has developed metrics and methods to measure and mitigate biases, which have been effectively applied to education as seen in the AI in education literature. What this paper adds Introduces a comprehensive technical framework for equity and inclusion, specifically for machine learning practitioners in AI education systems. Presents a novel modification to the ABROCA fairness metric to better represent disparities among multiple subgroups within a protected class. Empirical analysis of the effectiveness of bias‐mitigating techniques, like adversarial learning, in reducing biases in intersectional classes (eg, race–gender, race–income). Model reporting in the form of model cards that can foster transparent communication among developers, users and stakeholders. Implications for practice and/or policy The fairness framework can act as a systematic guide for practitioners to design equitable and inclusive AI‐EDSS. The fairness framework can act as a systematic guide for practitioners to make compliance with emerging AI regulations more manageable. Stakeholders may become more involved in tailoring the fairness and equity model tuning process to align with their values. What is already known about this topic AI‐powered Educational Decision Support Systems (EDSS) are increasingly used in various educational contexts, such as course selection, admissions, scholarship allocation and identifying at‐risk students. There are known challenges with AI in education, particularly around the reinforcement of existing biases, leading to unfair outcomes. The machine learning community has developed metrics and methods to measure and mitigate biases, which have been effectively applied to education as seen in the AI in education literature. What this paper adds Introduces a comprehensive technical framework for equity and inclusion, specifically for machine learning practitioners in AI education systems. Presents a novel modification to the ABROCA fairness metric to better represent disparities among multiple subgroups within a protected class. Empirical analysis of the effectiveness of bias‐mitigating techniques, like adversarial learning, in reducing biases in intersectional classes (eg, race–gender, race–income). Model reporting in the form of model cards that can foster transparent communication among developers, users and stakeholders. Implications for practice and/or policy The fairness framework can act as a systematic guide for practitioners to design equitable and inclusive AI‐EDSS. The fairness framework can act as a systematic guide for practitioners to make compliance with emerging AI regulations more manageable. Stakeholders may become more involved in tailoring the fairness and equity model tuning process to align with their values. [ABSTRACT FROM AUTHOR]

In order for teachers to successfully gain new knowledge during professional development (PD), courses must be of high quality and stimulate active involvement from participants. More and more PD courses are taking place online, without clear evidence of whether face‐to‐face and online courses differ in terms of their quality or level of participants' engagement. The present study investigates differences between face‐to‐face and online PD with respect to certain quality characteristics: clarity and structure, cognitive activation, collaboration and practical relevance, as well as participants' behavioural, cognitive and affective engagement. The study is based on 2210 teachers from Germany who participated in 1 of 137 face‐to‐face or 54 online PD courses. Although participants rated face‐to‐face and online courses very positively regarding all quality characteristics and engagement dimensions, they evaluated online courses slightly less favourably compared to face‐to‐face courses. Implications for practice and research are derived to help ensure high‐quality PD offerings in the future. Practitioner notes What is already known about this topic Face‐to‐face and online PD have the potential to be similarly effective. PD quality and participants' engagement can be assumed to be predictors of PD effectiveness. PD quality contains clarity and structure, cognitive activation, collaboration and practical relevance. Engagement is a three‐dimensional construct composed of behavioural, cognitive and affective components. What this paper adds PD quality was rated very positively for online and face‐to‐face courses. Participants rated the quality of online PD lower compared to face‐to‐face PD. Participants rated their engagement in online PD lower compared to face‐to‐face PD. Implications for practice and/or policy PD format should always be chosen with which a higher benefit can be achieved. Quality assurance should take place before PD is conducted. What is already known about this topic Face‐to‐face and online PD have the potential to be similarly effective. PD quality and participants' engagement can be assumed to be predictors of PD effectiveness. PD quality contains clarity and structure, cognitive activation, collaboration and practical relevance. Engagement is a three‐dimensional construct composed of behavioural, cognitive and affective components. What this paper adds PD quality was rated very positively for online and face‐to‐face courses. Participants rated the quality of online PD lower compared to face‐to‐face PD. Participants rated their engagement in online PD lower compared to face‐to‐face PD. Implications for practice and/or policy PD format should always be chosen with which a higher benefit can be achieved. Quality assurance should take place before PD is conducted. [ABSTRACT FROM AUTHOR]

Collaborative learning, driven by knowledge co‐construction and meaning negotiation, is a pivotal aspect of educational contexts. While gesture's importance in conveying shared meaning is recognized, its role in collaborative group settings remains understudied. This gap hinders accurate and equitable assessment and instruction, particularly for linguistically diverse students. Advancements in multimodal learning analytics, leveraging sensor technologies, offer innovative solutions for capturing and analysing body movements. This study employs these novel approaches to demonstrate how learners' machine‐detected body movements during the learning process relate to their verbal and nonverbal contributions to the co‐construction of embodied math knowledge. These findings substantiate the feasibility of utilizing learners' machine‐detected body movements as a valid indicator for inferring their engagement with the collaborative knowledge construction process. In addition, we empirically validate that these inferred different levels of learner engagement indeed impact the desired learning outcomes of the intervention. This study contributes to our scientific understanding of multimodal approaches to knowledge expression and assessment in learning, teaching, and collaboration.Practitioner notesWhat is already known about this topic Previous research emphasizes the importance of gestures as essential tools for constructing common ground and reflecting shared meaning‐making in learning and teaching contexts. The prior studies in multimodal learning analytics (MMLA) suggest that certain forms of body movements and postures can be differentiated based on the automatic detection of upper body joint locations. Empirical observations indicate that co‐thought gestures typically involve smaller hand or arms movement that are closer to the gesturer's body than co‐speech gestures used in interpersonal communication. What this paper adds This paper fills the research gap by examining the use of gestures in collaborative learning, offering insights into how individuals contribute verbally and nonverbally to collaborative knowledge construction. This paper introduces the concept of using machine‐detected body movements as a viable proxy for inferring learners' engagement in collaborative knowledge‐building activities. Leverages sensor technologies for automatic detection of body movements, the innovative approach in this work seeks to overcome the time‐intensive and laborious process of manually coding gestures. Implications for practice and/or policy By recognizing the potential significance of learners' body movements in indicating engagement levels with collaborative knowledge‐building activities, instructors can set up computer‐supported collaborative learning (CSCL) environments to enable capturing these movements. Given the crucial role of gestures in learning, teaching, and collaboration, educators can create more equitable formative assessment practices for linguistically diverse students by developing strategies that align with multimodal forms of knowledge expression. Research can expand beyond mathematics to explore the transferability of these findings to other subjects, helping educators create comprehensive pedagogical approaches that leverage multimodal interactions across disciplines. Previous research emphasizes the importance of gestures as essential tools for constructing common ground and reflecting shared meaning‐making in learning and teaching contexts. The prior studies in multimodal learning analytics (MMLA) suggest that certain forms of body movements and postures can be differentiated based on the automatic detection of upper body joint locations. Empirical observations indicate that co‐thought gestures typically involve smaller hand or arms movement that are closer to the gesturer's body than co‐speech gestures used in interpersonal communication. This paper fills the research gap by examining the use of gestures in collaborative learning, offering insights into how individuals contribute verbally and nonverbally to collaborative knowledge construction. This paper introduces the concept of using machine‐detected body movements as a viable proxy for inferring learners' engagement in collaborative knowledge‐building activities. Leverages sensor technologies for automatic detection of body movements, the innovative approach in this work seeks to overcome the time‐intensive and laborious process of manually coding gestures. By recognizing the potential significance of learners' body movements in indicating engagement levels with collaborative knowledge‐building activities, instructors can set up computer‐supported collaborative learning (CSCL) environments to enable capturing these movements. Given the crucial role of gestures in learning, teaching, and collaboration, educators can create more equitable formative assessment practices for linguistically diverse students by developing strategies that align with multimodal forms of knowledge expression. Research can expand beyond mathematics to explore the transferability of these findings to other subjects, helping educators create comprehensive pedagogical approaches that leverage multimodal interactions across disciplines. [ABSTRACT FROM AUTHOR]

Teaching and learning in higher education have increasingly become digitalized and associated with innovative pedagogical methodologies over the past decades. Following the sudden onset of the pandemic in March 2020, several studies tended to focus on traditional students' experiences with emergency remote education while literature is scarce on non‐traditional students (or adult learners) pedagogical experiences in Distance Education contexts. Using a qualitative case study approach, this study explored how digital technologies mediated instructors' and adult learners' educational experiences during COVID‐19 and their first‐time experiences with blended learning. Between October 2021 and July 2022, semi‐structured interviews were conducted with 40 adult learners and 20 instructors in three selected public higher education institutions (HEIs) in Ghana. Data analysis followed Braun and Clarke's (2012) thematic analysis approach. The results showed that the transition to blended learning was supported by the adoption and integration of varied virtual online technologies. The themes highlight the positive and negative impacts of technology in mediating the educational experiences of instructors and adult learners in blended learning environments. The themes which reflected both instructors' and adult learners' experiences were enhanced course delivery and pedagogy, competency development, technological issues and poor‐quality pedagogy. Blended learning facilitated by technology could be the ‘new normal learning’ post‐pandemic for adult learners pursuing Distance Education in Ghana. The study recommends the implementation of agile strategies and policies by HEIs to ensure sustainable quality education in distance learning. Practitioner notes What is already known about this topic The COVID‐19 pandemic necessitated the adoption of innovative pedagogical approaches in higher education contexts. Technological transformations in information and communication technology (ICT) have enhanced remote teaching in higher education institutions globally. The educational experiences of educators and learners differ in blended learning contexts. What this paper adds Instructors and adult learners' positive experiences with navigating a variety of web‐based technologies during the educational process are negatively impacted by technological difficulties during online instruction. Participants' experiences of blended learning are mixed with a preference for face‐to‐face dimension of blended learning instead of the online dimension. The paper identifies four themes that characterize instructors and adult learners' experiences with technology‐enhanced learning including enhanced course delivery and pedagogy, competency development, technological issues and poor‐quality pedagogy. Implications for practice and/or policy The study provides evidence‐based information on the relevance of digitizing distance education for sustainable development and promotion of lifelong learning opportunities for distance education students. The research recommends that higher education institutions (HEIs) implement agile policies to facilitate a seamless shift to distance learning. HEIs may adopt open distance learning frameworks to streamline 21st century pedagogical and learning practices in distance‐blended learning environments for quality course instruction. The study highlights the potential distance learning modalities that HEIs can consider for Distance Education students to sustain effective quality teaching and learning. What is already known about this topic The COVID‐19 pandemic necessitated the adoption of innovative pedagogical approaches in higher education contexts. Technological transformations in information and communication technology (ICT) have enhanced remote teaching in higher education institutions globally. The educational experiences of educators and learners differ in blended learning contexts. What this paper adds Instructors and adult learners' positive experiences with navigating a variety of web‐based technologies during the educational process are negatively impacted by technological difficulties during online instruction. Participants' experiences of blended learning are mixed with a preference for face‐to‐face dimension of blended learning instead of the online dimension. The paper identifies four themes that characterize instructors and adult learners' experiences with technology‐enhanced learning including enhanced course delivery and pedagogy, competency development, technological issues and poor‐quality pedagogy. Implications for practice and/or policy The study provides evidence‐based information on the relevance of digitizing distance education for sustainable development and promotion of lifelong learning opportunities for distance education students. The research recommends that higher education institutions (HEIs) implement agile policies to facilitate a seamless shift to distance learning. HEIs may adopt open distance learning frameworks to streamline 21st century pedagogical and learning practices in distance‐blended learning environments for quality course instruction. The study highlights the potential distance learning modalities that HEIs can consider for Distance Education students to sustain effective quality teaching and learning. [ABSTRACT FROM AUTHOR]

The adoption of large language models (LLMs) in education holds much promise. However, like many technological innovations before them, adoption and access can often be inequitable from the outset, creating more divides than they bridge. In this paper, we explore the magnitude of the country and language divide in the leading open‐source and proprietary LLMs with respect to knowledge of K‐12 taxonomies in a variety of countries and their performance on tagging problem content with the appropriate skill from a taxonomy, an important task for aligning open educational resources and tutoring content with state curricula. We also experiment with approaches to narrowing the performance divide by enhancing LLM skill tagging performance across four countries (the USA, Ireland, South Korea and India–Maharashtra) for more equitable outcomes. We observe considerable performance disparities not only with non‐English languages but with English and non‐US taxonomies. Our findings demonstrate that fine‐tuning GPT‐3.5 with a few labelled examples can improve its proficiency in tagging problems with relevant skills or standards, even for countries and languages that are underrepresented during training. Furthermore, the fine‐tuning results show the potential viability of GPT as a multilingual skill classifier. Using both an open‐source model, Llama2‐13B, and a closed‐source model, GPT‐3.5, we also observe large disparities in tagging performance between the two and find that fine‐tuning and skill information in the prompt improve both, but the closed‐source model improves to a much greater extent. Our study contributes to the first empirical results on mitigating disparities across countries and languages with LLMs in an educational context. Practitioner notes What is already known about this topic Recent advances in generative AI have led to increased applications of LLMs in education, offering diverse opportunities. LLMs excel predominantly in English and exhibit a bias towards the US context. Automated content tagging has been studied using English‐language content and taxonomies. What this paper adds Investigates the country and language disparities in LLMs concerning knowledge of educational taxonomies and their performance in tagging content. Presents the first empirical findings on addressing disparities in LLM performance across countries and languages within an educational context. Improves GPT‐3.5's tagging accuracy through fine‐tuning, even for non‐US countries, starting from zero accuracy. Extends automated content tagging to non‐English languages using both open‐source and closed‐source LLMs. Implications for practice and/or policy Underscores the importance of considering the performance generalizability of LLMs to languages other than English. Highlights the potential viability of ChatGPT as a skill tagging classifier across countries. What is already known about this topic Recent advances in generative AI have led to increased applications of LLMs in education, offering diverse opportunities. LLMs excel predominantly in English and exhibit a bias towards the US context. Automated content tagging has been studied using English‐language content and taxonomies. What this paper adds Investigates the country and language disparities in LLMs concerning knowledge of educational taxonomies and their performance in tagging content. Presents the first empirical findings on addressing disparities in LLM performance across countries and languages within an educational context. Improves GPT‐3.5's tagging accuracy through fine‐tuning, even for non‐US countries, starting from zero accuracy. Extends automated content tagging to non‐English languages using both open‐source and closed‐source LLMs. Implications for practice and/or policy Underscores the importance of considering the performance generalizability of LLMs to languages other than English. Highlights the potential viability of ChatGPT as a skill tagging classifier across countries. [ABSTRACT FROM AUTHOR]

The HyFlex course has been widely adopted in higher education settings. However, there is a paucity of empirical studies examining students' acceptance of large‐scale HyFlex courses, as well as factors influencing their acceptance. To fill this research gap, the present study investigated students' acceptance of a large‐scale HyFlex course and the variations in their acceptance according to different participation modes (ie, on‐site, synchronously online and mixed attendance), based on a total of 160 valid samples from a large‐scale HyFlex course at a normal university in central China during the fall semester of 2022. The results indicated that students' overall HyFlex course acceptance was generally high, and the students who alternately engaged in on‐site and synchronously online learning had the highest level of acceptance. Furthermore, this study employed structural equation modelling to validate a model integrating the unified theory of acceptance and use of technology with connected classroom climate (CCC). The findings showed that performance expectancy (PE), effort expectancy, facilitating conditions and CCC directly influenced students' acceptance, with performance expectancy having the strongest direct effect. However, social influence only had an indirect effect on students' acceptance, while CCC had both direct and indirect effects. This study carries substantial theoretical and practical implications, enhancing our understanding of students' acceptance of the HyFlex learning approach.Practitioner notesWhat is already known about this topic The adoption of the HyFlex course, especially in the context of large‐scale courses, is prevalent in higher education settings. Existing studies have predominately focused on assessing the impact of HyFlex course on student engagement and learning outcomes, the development and implementation of HyFlex course structures, and educators' perspectives and experiences with HyFlex courses. Although some research has delved into students' satisfaction with HyFlex courses, particularly in small class settings, our understanding of students' acceptance of large‐scale HyFlex course remains limited. There has been a noticeable gap in investigations exploring distinctions among students who opt for varying HyFlex course delivery modes, such as on‐site, synchronously online and mixed attendance formats. What this paper adds This study reveals that students generally displayed a high level of acceptance towards the large‐scale HyFlex course. Notably, students who participated in alternating on‐site and synchronously online learning exhibited a significantly higher level of acceptance towards the HyFlex course compared to their counterparts. A novel approach was employed in this study by integrating the UTAUT model with the concept of connected classroom climate (CCC) to comprehensively explore the key influencing factors and their interrelationships regarding students' acceptance of a large‐scale HyFlex course. The study found that performance expectancy (PE), effort expectancy (EE), facilitating conditions (FC) and CCC were all significant factors that positively influenced students' acceptance of the HyFlex course. Particularly, PE emerged as the factor with the strongest direct impact on HyFlex course acceptance (ACP). Interestingly, social influence (SI) did not exhibit a significant direct effect on students' ACP. However, it had a significant and positive indirect effect on students' ACP through the mediation of PE. Furthermore, CCC was shown to have both direct and indirect effects on students' acceptance of the HyFlex course, with the indirect effect of CCC on ACP accounted for nearly half of the total effect. Implications for practice and/or policy Instructors should prioritize emphasizing the advantages and benefits of HyFlex courses to enhance students' motivation and willingness to participate actively in these courses. This may involve showcasing how HyFlex course offer flexibility, convenience and varied learning opportunities. When implementing HyFlex courses, instructors should work to mitigate students' perceived EE. This could be achieved through streamlining course navigation, ensuring user‐friendly technology tools and providing clear guidelines for participation. Simultaneously, efforts should be made to enhance perceived learning support to facilitate students' engagement and acceptance of HyFlex courses. Instructors in HyFlex course settings should place a strong emphasis on creating a supportive and collaborative learning environment. This involves fostering interactions among students, encouraging peer‐to‐peer support and providing resources and guidance to help students navigate the challenges and opportunities presented by HyFlex course formats. Building a sense of community and connectedness among students can significantly impact their acceptance and success in such courses. What is already known about this topic The adoption of the HyFlex course, especially in the context of large‐scale courses, is prevalent in higher education settings. Existing studies have predominately focused on assessing the impact of HyFlex course on student engagement and learning outcomes, the development and implementation of HyFlex course structures, and educators' perspectives and experiences with HyFlex courses. Although some research has delved into students' satisfaction with HyFlex courses, particularly in small class settings, our understanding of students' acceptance of large‐scale HyFlex course remains limited. There has been a noticeable gap in investigations exploring distinctions among students who opt for varying HyFlex course delivery modes, such as on‐site, synchronously online and mixed attendance formats. What this paper adds This study reveals that students generally displayed a high level of acceptance towards the large‐scale HyFlex course. Notably, students who participated in alternating on‐site and synchronously online learning exhibited a significantly higher level of acceptance towards the HyFlex course compared to their counterparts. A novel approach was employed in this study by integrating the UTAUT model with the concept of connected classroom climate (CCC) to comprehensively explore the key influencing factors and their interrelationships regarding students' acceptance of a large‐scale HyFlex course. The study found that performance expectancy (PE), effort expectancy (EE), facilitating conditions (FC) and CCC were all significant factors that positively influenced students' acceptance of the HyFlex course. Particularly, PE emerged as the factor with the strongest direct impact on HyFlex course acceptance (ACP). Interestingly, social influence (SI) did not exhibit a significant direct effect on students' ACP. However, it had a significant and positive indirect effect on students' ACP through the mediation of PE. Furthermore, CCC was shown to have both direct and indirect effects on students' acceptance of the HyFlex course, with the indirect effect of CCC on ACP accounted for nearly half of the total effect. Implications for practice and/or policy Instructors should prioritize emphasizing the advantages and benefits of HyFlex courses to enhance students' motivation and willingness to participate actively in these courses. This may involve showcasing how HyFlex course offer flexibility, convenience and varied learning opportunities. When implementing HyFlex courses, instructors should work to mitigate students' perceived EE. This could be achieved through streamlining course navigation, ensuring user‐friendly technology tools and providing clear guidelines for participation. Simultaneously, efforts should be made to enhance perceived learning support to facilitate students' engagement and acceptance of HyFlex courses. Instructors in HyFlex course settings should place a strong emphasis on creating a supportive and collaborative learning environment. This involves fostering interactions among students, encouraging peer‐to‐peer support and providing resources and guidance to help students navigate the challenges and opportunities presented by HyFlex course formats. Building a sense of community and connectedness among students can significantly impact their acceptance and success in such courses. [ABSTRACT FROM AUTHOR]

In the ever‐evolving AI‐driven education, integrating AI technologies into teaching practices has become increasingly imperative for aspiring STEM educators. Yet, there remains a dearth of studies exploring pre‐service STEM teachers' readiness to incorporate AI into their teaching practices. This study examined the factors influencing teachers' willingness to integrate AI (WIAI), especially from the perspective of pre‐service STEM teachers' attitudes towards the application of AI in teaching. In the study, a comprehensive survey was conducted among 239 pre‐service STEM teachers, examining the influences and interconnectedness of Technological Pedagogical Content Knowledge (TPACK), Perceived Usefulness (PU), Perceived Ease of Use (PE), and Self‐Efficacy (SE) on WIAI. Structural Equation Modeling (SEM) was employed for data analysis. The findings illuminated direct influences of TPACK, PU, PE, and SE on WIAI. TPACK was found to directly affect PE, PU, and SE, while PE and PU also directly influenced SE. Further analysis revealed significant mediating roles of PE, PU, and SE in the relationship between TPACK and WIAI, highlighting the presence of a chain mediation effect. In light of these insights, the study offers several recommendations on promoting pre‐service STEM teachers' willingness to integrate AI into their teaching practices. Practitioner notes What is already known about this topic? The potential of AI technologies to enrich learning experiences and improve outcomes in STEM education has been recognized. Pre‐service teachers' willingness to integrate AI into teaching practice is crucial for shaping the future learning environment. The TAM and TPACK frameworks are used to analyse teacher factors in technology‐supported learning environments. Few studies have been conducted for examining factors of pre‐service teachers' willingness to integrate AI into teaching practices in the context of STEM education. What this paper adds? A survey was designed and developed for exploring pre‐service STEM teachers' WIAI and its relationships with factors including TPACK, PE, PU, and SE. TPACK, SE, PU, and PE have direct impact on pre‐service STEM teachers' WIAI. SE, PU, and PE have been identified as mediating variables in the relationship between TPACK and WIAI. Two sequential mediation effects, TPACK → PE → SE → WIAI and TPACK → PU → SE → WIAI, among pre‐service STEM teachers were further identified. Implications of this study for practice and/or policy Pre‐service STEM teachers are encouraged to explore and utilize AI technology to enhance their confidence and self‐efficacy in integrating AI into teaching practices. Showcasing successful cases and practical experiences is essential for fostering awareness of AI integration in STEM education. It is recommended to introduce AI education courses in teacher training programs. Offering internship and practicum opportunities related to AI technologies can enhance their practical skills in integrating AI into education. What is already known about this topic? The potential of AI technologies to enrich learning experiences and improve outcomes in STEM education has been recognized. Pre‐service teachers' willingness to integrate AI into teaching practice is crucial for shaping the future learning environment. The TAM and TPACK frameworks are used to analyse teacher factors in technology‐supported learning environments. Few studies have been conducted for examining factors of pre‐service teachers' willingness to integrate AI into teaching practices in the context of STEM education. What this paper adds? A survey was designed and developed for exploring pre‐service STEM teachers' WIAI and its relationships with factors including TPACK, PE, PU, and SE. TPACK, SE, PU, and PE have direct impact on pre‐service STEM teachers' WIAI. SE, PU, and PE have been identified as mediating variables in the relationship between TPACK and WIAI. Two sequential mediation effects, TPACK → PE → SE → WIAI and TPACK → PU → SE → WIAI, among pre‐service STEM teachers were further identified. Implications of this study for practice and/or policy Pre‐service STEM teachers are encouraged to explore and utilize AI technology to enhance their confidence and self‐efficacy in integrating AI into teaching practices. Showcasing successful cases and practical experiences is essential for fostering awareness of AI integration in STEM education. It is recommended to introduce AI education courses in teacher training programs. Offering internship and practicum opportunities related to AI technologies can enhance their practical skills in integrating AI into education. [ABSTRACT FROM AUTHOR]

Digital games (DGs) have the potential to immerse learners in simulated real‐world environments that foster contextualised and active learning experiences. These also offer opportunities for performance assessments by providing an environment for students to carry out tasks requiring the application of knowledge and skills learned in the classroom. Although widely used for teaching and learning, there are challenges in using digital game applications for assessment. Designing assessments around tasks in complex learning environments like DGs is not always easy, particularly for educators new to using these technologies for teaching. This paper presents a game‐based assessment framework (GBAF) that is designed to be educator‐friendly and useful for the design of assessments for immersive learning environments. The application of the framework to the design of embedded and external (multiple‐choice questions) assessments is also presented. The GBAF offered an easy and structured basis for the design of two distinct assessments for a computer game. It provides educators with useful guidelines for designing assessments around pre‐existing games. Practitioner notesWhat is already known about this topicImmersive technologies are increasingly being used for teaching and learning due to their benefits to knowledge and skills acquisition. However, for educators interested in using these tools for formal classroom teaching, there is a lack of resources and guidance on assessment designs and implementations. The most commonly used assessment design framework, the evidence‐centred design (ECD), is complicated to use, requiring advanced machine learning skills to implement. This has so far limited its use to large‐scale computerised and game‐based testing.What this paper addsThis paper presents a framework developed to guide educators through the design and implementation of assessments when teaching with immersive learning applications. Grounded in the constructive alignment principles and the ECD framework, the game‐based assessment framework is designed to help educators align assessment tasks to game tasks and the intended learning outcomes. It also provides step‐by‐step guidelines for the identification of appropriate immersive applications. It shows the practical application of the framework to the design of embedded (in‐game) assessments and external (multiple‐choice tests) assessments.Implications for practice and/or policyThe framework presented in this paper provides a structured and pedagogically sound basis for the design of assessments when measuring performance, or skills and knowledge acquisition with immersive learning applications. [ABSTRACT FROM AUTHOR]

This paper provides an experience report on a co‐design approach with teachers to co‐create learning analytics‐based technology to support problem‐based learning in middle school science classrooms. We have mapped out a workflow for such applications and developed design narratives to investigate the implementation, modifications and temporal roles of the participants in the design process. Our results provide precedent knowledge on co‐designing with experienced and novice teachers and co‐constructing actionable insight that can help teachers engage more effectively with their students' learning and problem‐solving processes during classroom PBL implementations. Practitioner notesWhat is already known about this topic Success of educational technology depends in large part on the technology's alignment with teachers' goals for their students, teaching strategies and classroom context.Teacher and researcher co‐design of educational technology and supporting curricula has proven to be an effective way for integrating teacher insight and supporting their implementation needs.Co‐designing learning analytics and support technologies with teachers is difficult due to differences in design and development goals, workplace norms, and AI‐literacy and learning analytics background of teachers.What this paper adds We provide a co‐design workflow for middle school teachers that centres on co‐designing and developing actionable insights to support problem‐based learning (PBL) by systematic development of responsive teaching practices using AI‐generated learning analytics.We adapt established human‐computer interaction (HCI) methods to tackle the complex task of classroom PBL implementation, working with experienced and novice teachers to create a learning analytics dashboard for a PBL curriculum.We demonstrate researcher and teacher roles and needs in ensuring co‐design collaboration and the co‐construction of actionable insight to support middle school PBL.Implications for practice and/or policy Learning analytics researchers will be able to use the workflow as a tool to support their PBL co‐design processes.Learning analytics researchers will be able to apply adapted HCI methods for effective co‐design processes.Co‐design teams will be able to pre‐emptively prepare for the difficulties and needs of teachers when integrating middle school teacher feedback during the co‐design process in support of PBL technologies. [ABSTRACT FROM AUTHOR]

This paper describes a Human‐Centred Learning Analytics (HCLA) design approach for developing learning analytics (LA) dashboards for K‐12 classrooms that maintain both contextual relevance and scalability—two goals that are often in competition. Using mixed methods, we collected observational and interview data from teacher partners and assessment data from their students' engagement with the lesson materials. This DBR‐based, human‐centred design process resulted in a dashboard that supported teachers in addressing their students' learning needs. To develop the dashboard features that could support teachers, we found that a design refinement process that drew on the insights of teachers with varying teaching experience, philosophies and teaching contexts strengthened the resulting outcome. The versatile nature of the approach, in terms of student learning outcomes, makes it useful for HCLA design efforts across diverse K‐12 educational contexts. Practitioner notesWhat is already known about this topic Learning analytics that are aligned to both a learning theory and learning design support student learning.LA dashboards that support users to understand the associated learning analytics data provide actionable insight.Design‐based research is a promising methodology for Human‐Centred Learning Analytics design, particularly in the K‐12 educational context.What this paper adds Leveraging a longstanding, yet fluid, research‐practice partnership is an effective design‐based research adaptation for addressing the high variation in instructional practices that characterize K‐12 education.Using both quantitative and qualitative data that reflects students' developing knowledge effectively supports teachers' inquiry into student learning.Teachers' use of learning analytics dashboards is heavily influenced by their perspectives on teaching and learning.Implications for practice and/or policy Impact on student learning outcomes, alongside usability and feasibility, should be included as a necessary metric for the effectiveness of LA design.LA dashboard developers should both leverage learning data that reflect students' developing knowledge and position teachers to take responsive pedagogical action to support student learning.LA researchers and developers should utilize a long‐term, yet fluid, research‐practice partnership to form a multi‐stakeholder, multidisciplinary design team for Human‐Centred Learning Analytics design. [ABSTRACT FROM AUTHOR]

Several studies have indicated that stakeholder engagement could ensure the successful adoption of learning analytics (LA). Considering that researchers and tech developers may not be aware of how LA tools can derive meaningful and actionable information for everyday use, these studies suggest that participatory approaches based on human‐centred design can provide stakeholders with the opportunity to influence decision‐making during tool development. So far, there is a growing consensus about the importance of identifying stakeholders' needs and expectations in early stages, so researchers and developers can design systems that resonate with their users. However, human‐centred LA is a growing sub‐field, so further empirical work is needed to understand how stakeholders can contribute effectively to the design process and the adoption strategy of analytical tools. To illustrate mechanisms to engage various stakeholders throughout different phases of a design process, this paper presents a multiple case study conducted in different Latin American universities. A series of studies inform the development of an analytical tool to support continuous curriculum improvement, aiming to improve student learning and programme quality. Yet, these studies differ in scope and design stage, so they use different mechanisms to engage students, course instructors and institutional administrators. By cross analysing the findings of these three cases, three conclusions emerged for each design phase of a CA tool, presenting mechanisms to ensure stakeholder adoption after tool development. Further implications of this multiple case study are discussed from a theoretical and methodological perspective. Practitioner notesWhat is already known about this topic? Human‐centred learning analytics (LA) has accommodated different configurations of stakeholder engagement, including co‐design and participatory design.Participatory design provides developers with a wide variety of techniques to engage a particular group in a mutual learning process.Most studies mainly focus on engaging stakeholders to identify needs in the early stages of the design process.More empirical works are needed to unveil the effectiveness of human centredness during LA design and after tool development.What this paper adds? Provides a multiple case study to illustrate mechanisms to engage various stakeholders in different design phases of a curriculum analytics (CA) tool.Summarises different assertions based on case study findings regarding needs for analytical tool, its early evaluation and its potential use after development.Provides empirical evidence on how to promote stakeholder engagement at a specific design stage and for a specific purpose.The implications for practitioners LA researchers and developers can use assertions based on evidence as a starting point to drive the design process of CA solutions.Researchers and practitioners will have a set of protocols to implement participatory techniques in different design phases of a CA tool. [ABSTRACT FROM AUTHOR]

Gamification, characterized by the integration of game design elements into non‐game environments, has gained popularity in classrooms due to its potential for increased engagement and enjoyment compared to traditional lecture‐based teaching methods. While students generally exhibit positive attitudes towards gamification, its impact on academic achievement remains a subject of debate. This study employed a meta‐analysis approach to examine the overall influence of gamification on students' academic performance. The sample comprised 22 experimental studies conducted between 2008 and 2023, comparing the effects of gamified and non‐gamified classes. Utilizing a random effects model, the results revealed a moderately positive effect of gamification on student academic performance (Hedges's g = 0.782, p < 0.05). The paper further discussed the outcomes of various moderator analyses, providing valuable insights into the selection and utilization of game design elements, as well as considerations specific to different educational stages.Practitioner notesWhat is already known about this topic Most research has consistently demonstrated that gamification has a positive impact on students' achievement. The current state of review research is not sufficiently comprehensive. There is a lack of meta‐analyses exploring the diverse impacts of gamification. What this paper adds The effect of factors such as geographical regions, education levels, learning environments, subjects and game elements on gamification was examined. The study revealed a significant and positive impact of gamification on students' achievement across various factors, including geographical regions, education levels, learning environments, subjects and game elements. Implications for practice and/or policy Gamification represents a prudent choice for teachers seeking to enhance students' achievement. Teachers are suggested to adopt and employ appropriate game elements in their instructional approaches. Future research could focus on investigating the impact of feedback as a game element in teaching and learning. Most research has consistently demonstrated that gamification has a positive impact on students' achievement. The current state of review research is not sufficiently comprehensive. There is a lack of meta‐analyses exploring the diverse impacts of gamification. The effect of factors such as geographical regions, education levels, learning environments, subjects and game elements on gamification was examined. The study revealed a significant and positive impact of gamification on students' achievement across various factors, including geographical regions, education levels, learning environments, subjects and game elements. Gamification represents a prudent choice for teachers seeking to enhance students' achievement. Teachers are suggested to adopt and employ appropriate game elements in their instructional approaches. Future research could focus on investigating the impact of feedback as a game element in teaching and learning. [ABSTRACT FROM AUTHOR]

Despite the importance of academic counselling for student success, providing timely and personalized guidance can be challenging for higher education institutions. In this study, we investigate the impact of counselling instances supported by a learning analytics (LA) tool, called TrAC, which provides specific data about the curriculum and grades of each student. To evaluate the tool, we measured changes in students' performance ranking position over 3 years and compared the performance of students who received counselling with and without the tool. Our results show that using the tool is related to an improvement in cohort ranking. We further investigated the characteristics of counselled students using cluster analyses. The findings highlight the potential beneficial influence on academic outcomes arising from the provision of guidance to students regarding their course load decisions via TrAC‐mediated counselling. This study contributes to the field of LA by providing evidence of the impact of counselling supported by an LA tool in a real‐world setting over a long period of time. Our results suggest that incorporating LA into academic counselling practices can improve student success. Practitioner notes What is already known about this topic By analysing student performance, teaching strategies and resource impact, learning analytics (LA) empowers institutions to make informed changes in curriculum design, resource allocation and educational policies. Through insights into academic progress, engagement and behaviour, LA counselling tools enable the identification of at‐risk students and those needing additional support. In the related literature, there are areas for further exploration such as understanding the scalability and long‐term effects of interventions on student success and retention. What this paper adds Through rigorous data analysis, the paper establishes a connection between LA utilization and enhanced student performance, offering concrete evidence of the effectiveness of LA interventions. By examining various factors such as academic stage and course load, the research offers valuable insights into the contextual nuances that optimize the outcomes of LA tool‐based support. It adds to the growing body of evidence that supports the efficacy of data‐driven interventions in education, fostering a more informed and evidence‐based approach to student support and success. Implications for practice and policy Enhanced student support strategies: By tailoring counselling interventions to align with the identified effective conditions, educators can proactively address individual student needs, improving academic outcomes and retention rates. Informed decision making: The demonstrated positive impact highlights the potential of similar data‐driven initiatives to foster student success. Policymakers can consider incentivizing the adoption of such interventions at institutional levels. Future directions for research: By identifying contextual factors that influence the efficacy of LA interventions, it encourages further exploration into how other LA interventions can be optimized for specific conditions. This can guide the development of more precise and effective student support strategies in the future. What is already known about this topic By analysing student performance, teaching strategies and resource impact, learning analytics (LA) empowers institutions to make informed changes in curriculum design, resource allocation and educational policies. Through insights into academic progress, engagement and behaviour, LA counselling tools enable the identification of at‐risk students and those needing additional support. In the related literature, there are areas for further exploration such as understanding the scalability and long‐term effects of interventions on student success and retention. What this paper adds Through rigorous data analysis, the paper establishes a connection between LA utilization and enhanced student performance, offering concrete evidence of the effectiveness of LA interventions. By examining various factors such as academic stage and course load, the research offers valuable insights into the contextual nuances that optimize the outcomes of LA tool‐based support. It adds to the growing body of evidence that supports the efficacy of data‐driven interventions in education, fostering a more informed and evidence‐based approach to student support and success. Implications for practice and policy Enhanced student support strategies: By tailoring counselling interventions to align with the identified effective conditions, educators can proactively address individual student needs, improving academic outcomes and retention rates. Informed decision making: The demonstrated positive impact highlights the potential of similar data‐driven initiatives to foster student success. Policymakers can consider incentivizing the adoption of such interventions at institutional levels. Future directions for research: By identifying contextual factors that influence the efficacy of LA interventions, it encourages further exploration into how other LA interventions can be optimized for specific conditions. This can guide the development of more precise and effective student support strategies in the future. [ABSTRACT FROM AUTHOR]

Previous research has demonstrated the effectiveness of executive functions (EFs) training, both in computer‐based and school‐based formats. However, there is limited research on the combined effects of these training modalities. This study aims to assess the feasibility and preliminary efficacy of an EFs training programme for primary school children. The programme includes computerized training sessions for home use and school activities with metacognitive elements. The study included a sample of 53 second‐grade children, with 21 children in the training group and 32 children in the control group. Feasibility questionnaires were completed by children, parents and teachers. The children also underwent an EFs evaluation. The results indicate that the training was enjoyable for children and feasible for parents and teachers. Furthermore, preliminary efficacy analysis revealed significant improvements in working memory. These findings suggest that the training model holds promise for enhancing EFs in children in the school context. Practitioner notes What is already known about this topic Individual differences in executive functions influence acquisitions, behaviours and competencies in several specific domains from infancy to adulthood. Enhancing executive functions during school‐age years can contribute to reducing or preventing academic, behavioural and social difficulties. Among interventions targeting executive functions in school‐aged children, school‐based interventions have shown the highest effectiveness, followed by metacognitive interventions and computer‐based interventions. What this paper adds This paper presents the implementation of an innovative school‐based training programme designed to improve executive functions (EFs). The programme combines metacognitive sessions conducted at school with computer‐based sessions carried out at home. The goal was to enhance the effectiveness and generalizability of the training. The training programme was found to be enjoyable for children and feasible for both parents and teachers. Preliminary efficacy data indicate promising results, suggesting that the training programme is effective in achieving its intended goals. Implications for practice and/or policy Integrating school‐based metacognitive training with computerized sessions delivered at home can provide a high‐intensity training programme that may not be achievable in the school context alone. The school activities, conducted in group settings with teachers and peers, were found to be the most appreciated by the children, indicating that computer sessions alone cannot replace the value of metacognitive sessions at school, within a meaningful social context for the child. It is crucial to actively involve families in the training process to ensure good adherence. Additionally, the availability of technological resources in each family should be evaluated before implementing the training programme. What is already known about this topic Individual differences in executive functions influence acquisitions, behaviours and competencies in several specific domains from infancy to adulthood. Enhancing executive functions during school‐age years can contribute to reducing or preventing academic, behavioural and social difficulties. Among interventions targeting executive functions in school‐aged children, school‐based interventions have shown the highest effectiveness, followed by metacognitive interventions and computer‐based interventions. What this paper adds This paper presents the implementation of an innovative school‐based training programme designed to improve executive functions (EFs). The programme combines metacognitive sessions conducted at school with computer‐based sessions carried out at home. The goal was to enhance the effectiveness and generalizability of the training. The training programme was found to be enjoyable for children and feasible for both parents and teachers. Preliminary efficacy data indicate promising results, suggesting that the training programme is effective in achieving its intended goals. Implications for practice and/or policy Integrating school‐based metacognitive training with computerized sessions delivered at home can provide a high‐intensity training programme that may not be achievable in the school context alone. The school activities, conducted in group settings with teachers and peers, were found to be the most appreciated by the children, indicating that computer sessions alone cannot replace the value of metacognitive sessions at school, within a meaningful social context for the child. It is crucial to actively involve families in the training process to ensure good adherence. Additionally, the availability of technological resources in each family should be evaluated before implementing the training programme. [ABSTRACT FROM AUTHOR]

Deep neural networks are increasingly employed to model classroom dialogue and provide teachers with prompt and valuable feedback on their teaching practices. However, these deep learning models often have intricate structures with numerous unknown parameters, functioning as black boxes. The lack of clear explanations regarding their classroom dialogue analysis likely leads teachers to distrust and underutilize these AI‐powered models. To tackle this issue, we leveraged explainable AI to unravel classroom dialogue analysis and conducted an experiment to evaluate the effects of explanations. Fifty‐nine pre‐service teachers were recruited and randomly assigned to either a treatment (n = 30) or control (n = 29) group. Initially, both groups learned to analyse classroom dialogue using AI‐powered models without explanations. Subsequently, the treatment group received both AI analysis and explanations, while the control group continued to receive only AI predictions. The results demonstrated that teachers in the treatment group exhibited significantly higher levels of trust in and technology acceptance of AI‐powered models for classroom dialogue analysis compared to those in the control group. Notably, there were no significant differences in cognitive load between the two groups. Furthermore, teachers in the treatment group expressed high satisfaction with the explanations. During interviews, they also elucidated how the explanations changed their perceptions of model features and attitudes towards the models. This study is among the pioneering works to propose and validate the use of explainable AI to address interpretability challenges within deep learning‐based models in the context of classroom dialogue analysis.Practitioner notesWhat is already known about this topic Classroom dialogue is recognized as a crucial element in the teaching and learning process. Researchers have increasingly utilized AI techniques, particularly deep learning methods, to analyse classroom dialogue. Deep learning‐based models, characterized by their intricate structures, often function as black boxes, lacking the ability to provide transparent explanations regarding their analysis. This limitation can result in teachers harbouring distrust and underutilizing these models. What this paper adds This paper highlights the importance of incorporating explainable AI approaches to tackle the interpretability issues associated with deep learning‐based models utilized for classroom dialogue analysis. Through an experimental study, this paper demonstrates that providing model explanations enhances teachers' trust in and technology acceptance of AI‐powered classroom dialogue models, without increasing their cognitive load. Teachers express satisfaction with the model explanations provided by explainable AI. Implications for practice and/or policy The integration of explainable AI can effectively address the challenge of interpretability in complex AI‐powered models used for analysing classroom dialogue. Intelligent teaching systems designed for classroom dialogue can benefit from advanced AI models and explainable AI approaches, which offer users both automated analysis and clear explanations. By enabling users to understand the underlying rationale behind the analysis, the explanations can contribute to fostering trust and acceptance of the AI models among users. Classroom dialogue is recognized as a crucial element in the teaching and learning process. Researchers have increasingly utilized AI techniques, particularly deep learning methods, to analyse classroom dialogue. Deep learning‐based models, characterized by their intricate structures, often function as black boxes, lacking the ability to provide transparent explanations regarding their analysis. This limitation can result in teachers harbouring distrust and underutilizing these models. This paper highlights the importance of incorporating explainable AI approaches to tackle the interpretability issues associated with deep learning‐based models utilized for classroom dialogue analysis. Through an experimental study, this paper demonstrates that providing model explanations enhances teachers' trust in and technology acceptance of AI‐powered classroom dialogue models, without increasing their cognitive load. Teachers express satisfaction with the model explanations provided by explainable AI. The integration of explainable AI can effectively address the challenge of interpretability in complex AI‐powered models used for analysing classroom dialogue. Intelligent teaching systems designed for classroom dialogue can benefit from advanced AI models and explainable AI approaches, which offer users both automated analysis and clear explanations. By enabling users to understand the underlying rationale behind the analysis, the explanations can contribute to fostering trust and acceptance of the AI models among users. [ABSTRACT FROM AUTHOR]

This study addresses the need for inclusive AI education by focusing on marginalized female students who historically lack access to learning opportunities in computing. It applies the theoretical framework of intersectionality to understand how gender, race and ethnicity intersect to shape these students' learning experiences and outcomes. Specifically, this study investigated 27 high‐school students' cognitive engagement in machine learning practices. We conducted the Wilcoxon–Mann–Whitney test to explore differences in cognitive engagement between marginalized female students and their peers, employed comparative content analysis to delve into significant differences and analysed interview data thematically to gain deeper insights into students' machine learning model development processes. The findings indicated that, when engaging in machine learning practices requiring drawing diverse cultural perspectives, marginalized female students demonstrated significantly higher performance compared to their peers. In particular, marginalized female students exhibited strengths in holistic language analysis, paying attention to writers' intentions and recognizing cultural nuances in language. This study suggests that integrating language analysis and machine learning across subjects has the potential to empower marginalized female students and amplify their perspectives. Furthermore, it calls for a strengths‐based approach to reshape the narrative of underrepresentation and promote equitable participation in machine learning and AI. Practitioner notes What is already known about this topic Female students, particularly those from underrepresented groups such as African American and Latina students, often experience low levels of cognitive engagement in computing. Marginalized female students possess unique strengths that, when nurtured, have the potential to not only transform their own learning experiences but also contribute to the advancement of the computing field. It is critical to empower marginalized female students in K‐12 AI (ie, a subfield of computing) education, seeking to bridge the gender and racial disparity in AI. What this paper adds Marginalized female students outperformed their peers in responding to machine learning questions related to feature analysis and feature distribution interpretation. When responding to these questions, they demonstrated a holistic approach to analysing language by considering interactions between features and writers' intentions. They drew on knowledge about how language was used to convey meaning in different cultural contexts. Implications for practice and/or policy Educators should design learning environments that encourage students to draw upon their cultural backgrounds, linguistic insights and diverse experiences to enhance their engagement and performance in AI‐related activities. Educators should strategically integrate language analysis and machine learning across different subjects to create interdisciplinary learning experiences that support students' exploration of the interplay among language, culture and AI. Educational institutions and policy initiatives should adopt a strengths‐based approach that focuses on empowering marginalized female students by acknowledging their inherent abilities and diverse backgrounds. What is already known about this topic Female students, particularly those from underrepresented groups such as African American and Latina students, often experience low levels of cognitive engagement in computing. Marginalized female students possess unique strengths that, when nurtured, have the potential to not only transform their own learning experiences but also contribute to the advancement of the computing field. It is critical to empower marginalized female students in K‐12 AI (ie, a subfield of computing) education, seeking to bridge the gender and racial disparity in AI. What this paper adds Marginalized female students outperformed their peers in responding to machine learning questions related to feature analysis and feature distribution interpretation. When responding to these questions, they demonstrated a holistic approach to analysing language by considering interactions between features and writers' intentions. They drew on knowledge about how language was used to convey meaning in different cultural contexts. Implications for practice and/or policy Educators should design learning environments that encourage students to draw upon their cultural backgrounds, linguistic insights and diverse experiences to enhance their engagement and performance in AI‐related activities. Educators should strategically integrate language analysis and machine learning across different subjects to create interdisciplinary learning experiences that support students' exploration of the interplay among language, culture and AI. Educational institutions and policy initiatives should adopt a strengths‐based approach that focuses on empowering marginalized female students by acknowledging their inherent abilities and diverse backgrounds. [ABSTRACT FROM AUTHOR]