Search

Exploratory data analysis (EDA), data visualization, and visual analytics are essential for understanding and analyzing complex datasets. In this project, we explored these techniques and their applications in data analytics. The case discusses Tableau, a powerful data visualization tool, and Google BigQuery, a cloud-based data warehouse that enables users to store, query, and analyze large datasets. It also explored the benefits and applications of both tools and their integration with other platforms and services. The project offers an introductory insight into Tableau's functionalities, employing a data file from the US Census Bureau via Google BigQuery.

Assessment is an important component of learning which aims to determine student achievement in learning. However, the pandemic has changed how assessment is carried out, prompting teachers to look for new strategies in carrying out mathematics learning assessments under any conditions, whether in normal conditions or during a pandemic. This study described the strategies used by high school mathematics teachers in assessing mathematics learning during the pandemic towards the post-pandemic period. This type of research is descriptive exploratory research with a qualitative approach. The subjects in this study were three mathematics teachers, three principals, and three vice principals from a public senior high school in Yogyakarta City, Indonesia. Qualitative data were collected by means of questionnaires, interviews, and documentation. The collected data were analyzed qualitatively according to Bogdan and Biklen. The results of the study reveal that the mathematics teacher's strategy for carrying out assessments during a pandemic includes: i) determining the appropriate online assessment platform that suits the needs; ii) assessment based on student participation; iii) using various of online assessment methods; iv) prioritizing academic integrity and honesty in the assessment implementation; and v) carry out the management and reporting of data on the results of the assessment in accordance with established procedures.

In the current era, the E-Government phenomenon, which describes the state's provision of public services to its stakeholders through information and communication technologies, has a global character. This study aimed to examine the big data-based e-Government portal, which has many examples in the world and was created by utilizing digital technologies, on the example of the Turkish Republic of Northern Cyprus (TRNC), and whether the portal is user-oriented or not was examined by content analysis method in the context of big data features and citizen-oriented. The absence of any other study on the examination of the TRNC E-Government Portal, which was reorganized in 2021, gives the study a unique quality. At the end of the study, although progress was observed in the information and transaction stages of the TRNC E-Government Portal in the context of e-Government models, it has been determined that success has not yet been achieved in the interaction and integration stages, as well as in the context of citizen-oriented and big data features, it has been concluded that there is not enough level for a successful government portal.

The prediction of student performance and the analysis of students' learning behaviour play an important role in enhancing online courses. By analysing a massive amount of clickstream data that captures student behaviour, educators can gain valuable insights into the factors that influence students' academic outcomes and identify areas of improvement in courses. In this study, we developed ClickTree, a tree-based methodology, to predict student performance in mathematical problems in end-unit assignments based on students' clickstream data. Utilising extensive clickstream data, we extracted a novel set of features at three levels, including problem-level, assignment-level and student-level, and we trained a CatBoost tree to predict whether a student will successfully answer a problem in an end-unit assignment or not. The developed method achieved an Area under the ROC Curve (AUC) of approximately 79% in the Educational Data Mining Cup 2023 and ranked second in the competition. Our results indicate that students who performed well in end-unit assignment problems engaged more with in-unit assignments and answered more problems correctly, while those who struggled had higher tutoring request rates. We also found that students face more difficulties with "check all that apply" types of problems. Moreover, Algebra II was the most difficult subject for students. The proposed method can be utilised to improve students' learning experiences, and the insights from this study can be integrated into mathematics courses to enhance students' learning outcomes.

Knowledge tracing aims to model and predict students' knowledge states during learning activities. Traditional methods like Bayesian Knowledge Tracing (BKT) and logistic regression have limitations in granularity and performance, while deep knowledge tracing (DKT) models often suffer from lacking transparency. This paper proposes a Transformer-based framework that emphasizes both accuracy and interpretability. It captures the relationship between student behaviors and learning outcomes considering the associations between exam and exercise problems. We participated in the EDM Cup 2023 Contest using the proposed framework and achieved first place on the task of predicting students' performance on end-of-unit test problems using clickstream data from previous assignments. Furthermore, the framework provides meaningful insights by analyzing user actions and visualizing attention weight matrices. These insights enable targeted interventions and personalized support, enhancing online learning experiences. We have uploaded our code, saved models, and predictions to an OSF repository: https://osf.io/mdpzc/.

Colleges and universities depend upon external approvals from accreditors, government agencies, and national organizations. These approvals require periodic review of institution-prepared reports and self-studies documenting the continued validity of offered degrees and programs, student support and success, institutional effectiveness, and continuous improvement. Campus leaders generally take one of two approaches to complete this work: deploying working groups and committees or relying on one or two institutional accreditation leaders. This 2024 AALHE Conference session introduced a third approach, a hybrid of the two dominant approaches, which begins with a campus-wide assets-based exercise for gathering information and evidence. Deploying the exercise decreases the time campus stakeholders must commit to these recurring external review processes; provides accreditation leaders with information and evidence that reflect the breadth of the institution's activities; addresses the problem of a narrow interpretation of assessment activities; and is more effective in the current higher education milieu where institutional effectiveness and continuous improvement are embedded across the breadth of institutionally unique activities.

The power of sport to affect social change is widely acknowledged. However, little empirical research has explored the use of sport in engaging young people in global education. This article fills the gap by exploring the role of sport using experiential learning tools as delivery methodology for global education in the context of Central Europe (Czechia). The study focuses on the experiential learning process of the study participants, a mixed intercultural team of Czech and Kenyan youth ambassadors participating in a Football for Development project with the aim of engendering cultural understanding, respecting diversity as positive and valuing differences as beneficial to society. The study benefited from a newly developed non-conventional data collection tool enhancing the research methodology and allowing for the facilitation of the participants' ability to discover and process the experience-related learning through reflexivity. By showing the changes in knowledge, skills, values and attitudes, our findings indicate how the sport for development programme contributes to creating a semi-conscious learning environment for global education.

Cooperative Extension professionals utilize proven qualitative techniques to collect and analyze information to make data-driven decisions that guide program direction and determine impact. While the process may not always look the same, it is indeed essential to ensure findings are credible and reflective of the data. A codebook is a valuable tool that promotes interrater reliability among teams and enhances the reliability of findings. This article provides an overview of the process used to analyze qualitative data and the steps followed to create a codebook. Examples of the analysis process and codebook development are provided from the 4-H multi-state Youth Retention Study.

Remote technology has been widely incorporated into health professions education. For procedural skills training, effective feedback and reflection processes are required. Consequently, supporting a self-regulated learning (SRL) approach with learning analytics dashboards (LADs) has proven beneficial in online environments. Despite the potential of LADs, understanding their design to enhance SRL and provide useful feedback remains a significant challenge. Focusing on LAD design, implementation, and evaluation, the study followed a mixed-methods two-phase design-based research approach. The study used a triangulation methodology of qualitative interviews and SRL and sensemaking questionnaires to comprehensively understand the LAD's effectiveness and student SRL and feedback uptake strategies during remote procedural skills training. Initial findings revealed the value students placed on performance visualization and peer comparison despite some challenges in LAD design and usability. The study also identified the prominent adoption of SRL strategies such as help-seeking, elaboration, and strategic planning. Sensemaking results showed the value of personalized performance metrics and planning resources in the LAD and recommendations to improve reflection and feedback uptake. Subsequent findings suggested that SRL levels significantly predicted the levels of sensemaking. The students valued the LAD as a tool for supporting feedback uptake and strategic planning, demonstrating the potential for enhancing procedural skills learning.

Classroom sensing systems can capture data on teacher-student behaviours and interactions at a scale far greater than human observers can. These data, translated to multi-modal analytics, can provide meaningful insights to educational stakeholders. However, complex data can be difficult to make sense of. In addition, analyses done on these data are often limited by the organization of the underlying sensing system, and translating sensing data into meaningful insights often requires custom analyses across different modalities. We present Edulyze, an analytics engine that processes complex, multi-modal sensing data and translates them into a unified schema that is agnostic to the underlying sensing system or classroom configuration. We evaluate Edulyze's performance by integrating three sensing systems (Edusense, ClassGaze, and Moodoo) and then present data analyses of five case studies of relevant pedagogical research questions across these sensing systems. We demonstrate how Edulyze's flexibility and customizability allow us to answer a broad range of research questions made possible by Edulyze's translation of a breadth of raw sensing data from different sensing systems into relevant classroom analytics.

As part of a study investigating research productivity of sociology PhD students in Australia, an application to the federal government's Department of Education, Skills and Employment (DESE) aimed to establish a baseline count of completed sociology doctorates by university. It was anticipated that university totals might be different from PhD completions within the main sociology teaching units. The government data furnished by this inquiry have proved to be problematic in several ways. The gaps in the data may be explained by the fact that universities report sociology PhDs to DESE in more generic rather than discipline-specific Field of Education (FoE) codes or as PhDs in other disciplines. DESE has either not required or been able to enforce consistent reporting. This raises questions about the time and cost value of these annual compliance efforts. It also limits the value of these data to researchers in charting current and potential future trends.

In the present study, we examined the psychometric properties of the data obtained from the Commitment to Profession of Medicine Scale (CPMS) with 4-point, 5-point, 6-point, and 7-point response sets based on Item Response Theory (IRT). A total of 2150 medical students from 16 different universities participated in the study. The participants were divided into four groups consisting of 560, 544, 502, and 544 medical students. The first group (n=560) was assigned four-point, the second group (n=544) five-point, the third group (n=502) six-point, and the fourth group (n=544) seven-point Likert forms. We used R statistical software to analyze the data. The results of item calibrations conducted with the Graded Response Model (GRM) were analyzed. The results show that the eigenvalue increased from 4-point to 7-point. Similarly, the explained variance percentage and the scale's reliability increased gradually from 4-point to 7-point. The explained variance, reliability level, and eigenvalue were very close in the 5-point and 6-point forms.

The purpose of this essay is to discuss the impact of the EdD experience on one teacher's understanding of data and research. From a first-person narrative, the author shares how learning to collect and analyze qualitative data has the potential to change the way teachers can engage with "data-driven decision making" in a high school setting. By exploring one scholar practitioner's personal evolution demonstrates the potential of qualitative research as a tool for both teachers and site administrators tackling stubborn challenges on our campuses. Includes examples of qualitative data sets collected on site and how data informed and inspired further work.

Background: Knowledge brokering by intermediary organizations includes knowledge distillation processes (e.g., synthesis, translation). Aims and objectives: This article explores how an educational intermediary performs research distillation when creating virtual knowledge reservoirs for educators. Methods: The authors use qualitative data from semi-structured interviews, coded to consensus, and thematically analyzed. Findings: During synthesis, intermediaries apply a "research lens" to evaluate the credibility of the evidence. During translation, they rely on their experience as educators to share evidence in a non-academic voice and generate "turnkey" strategies. Discussion and conclusion: The article considers the knowledge brokering pipeline fallacy and examines the potential of ongoing processes for improving the effectiveness of intermediaries with the aim of diminishing research-practice and research-policy gaps in education.

The preschool years, spanning from birth to age six, are crucial periods for acquiring social-emotional learning (SEL) skills. An effective way to address social-emotional learning deficits is to implement evidence-based intervention programs. The purpose of this article is to review specific evidencebased social-emotional learning intervention programs for preschool children, drawing from resources such as books, peer-reviewed journal articles, and conference proceedings. In this context, five social-emotional learning intervention programs, including First Step to Success, I Can Problem Solve, Incredible Years, PATHS, and Strong Start Pre-K, documented in the social-emotional learning literature, were reviewed. Each program was evaluated based on its target group, duration, focus, delivery method, and experimental effects. The reviews found that play-based activities, puppets and stories, role-playing, and family involvement were common components of these programs. The majority of programs focused on problem-solving skills, and all had positive effects on preschoolers' social-emotional learning skills. Based on the reviews, it was underlined that social-emotional learning intervention programs are effective when their content, process, and delivery methods are developmentally appropriate for the target group. Accordingly, it was seen that the widespread implementation of evidence-based social-emotional learning intervention programs is essential to improve the basic social-emotional learning skills of preschool children and to address their potential deficits. Continuous evaluation and refinement of social-emotional learning intervention programs, guided by feedback from educators, parents, and researchers, was also highlighted as crucial to increase their impact. By prioritizing the implementation of evidence-based social-emotional learning intervention programs with appropriate components and delivery methods, the stakeholders of education can facilitate the holistic development of preschool children and lay a strong foundation for their future social-emotional well-being.

Big Data offers opportunities and challenges in all aspects of human life. In relation to research ethics, Big Data represents a normative difference in degree rather than a difference in kind. Data are more messy, rapid, difficult to predict, and difficult to identify owners; but the principles of informed consent, confidentiality, and prevention of harm apply equally to digital data. Recognition that technologies are not inherently value neutral, and that data collection, aggregation, and their use in decision making can both create and intensify inequities and harms is central to applying these principles. Data justice extends concern with voice and authenticity into the digital domain. Universities act as gatekeepers to professional accreditation in fields including software engineering. The relation between academic freedom of enquiry, state and corporate interests in the Big Data age raises important questions about power and control in the academy, which have governance implications.

Practitioner-focused educational doctoral programs have grown substantially in recent years. Dissertations in Practice (DiPs), which are the culminating research report and evaluation method in these programs, differ from traditional PhD dissertations in their focus on addressing a problem of practice and on connecting theories with practice. As part of our ongoing program evaluation, we reviewed DiPs from doctoral students who graduated from an online asynchronous Educational Doctoral program in Learning Design and Technologies at the University of South Carolina. Findings revealed that most students chose a pragmatic philosophical paradigm, adopted a mixed methods research design, reported an action research intervention implemented with populations in K-12 schools, used surveys and interviews as data sources, and analyzed data with descriptive/inferential statistics and thematic analysis. Implications for the program curriculum are discussed.

This research aimed to determine the trends related to blended learning studies conducted in science education through descriptive content analysis. This study was performed using the document review method. For this purpose, 120 studies on blended learning in science education were determined between 2005 and 2022 in the Web of Science (WoS) database. The studies were examined by considering themes such as keywords, country, purpose, method, sample, online system, and result. The research findings showed that more studies occurred between 2020 and 2022. The findings showed that studies mostly use quantitative research methods and experimental designs. Most of the studies were conducted with undergraduate-level sample groups. Findings revealed that the blended learning environment is designed more to teach physics subjects, and parametric tests were generally used for data analysis. The more preferred course management systems in the studies were the online systems designed by the schools. A considerable number of studies revealed that blended learning environments designed for science education have a positive effect on variables such as achievement, skill, and motivation.

This study explores the complexities of qualitative fieldwork and unpacks the fieldwork dynamics drawing on critical reflections based on the experiences of interviewing primary level teachers in exploring their identities. I argue that qualitative fieldwork is not a one-shot, linear activity but a negotiated and relational task requiring a flexible and context-specific plan. This study identifies challenges associated with the fieldwork relating to establishing and sustaining a good relationship and reciprocity between the researcher and the participants, unequal power dynamics between the researcher and the participants, participants' familiarity with and habitual response to the survey questionnaires, narrow understanding of confidentiality and anonymity as ethical considerations, unmatched gender between the researcher and the participants, and through and detailed capture of micro field jottings and writing the fieldnotes. I suggest initiating fieldwork with sufficient informal conversation and establishing a rapport to gain the participants' trust, positioning oneself as an insider to acquire valuable and meaningful data.

This review explores the integration and effects of the Internet of Things (IoT) in education, highlighting its importance in transforming traditional teaching and learning techniques. It examines the early uses and historical growth of IoT, its development, and the turning points in its adoption. It explores IoT platforms, tools, and technologies in education, including wearables, smart devices, augmented and virtual reality, gamification, and collaborative learning. It discusses the role of IoT in improving campus management, including intelligent campuses with IoT-enabled infrastructure, energy-saving technologies, and safety and security improvements. The study discusses data security and privacy issues in IoT installations and the ethical and legal implications of data collection in the classroom. The study also discusses upcoming trends and prospects for IoT usage in education, including AI and machine learning integration. Finally, the review provides insights for educators, decision-makers, and stakeholders, identifying research gaps and recommending areas for future IoT implementation.

Northeastern University's EdD faculty faced unique challenges during the pandemic and racial reckoning following George Floyd's murder. During this period, however, we found opportunities to adapt and improve our program. We prioritized compassion and connection. We made significant strides in curriculum development through design and implementation of three new concentrations. We focused all program elements on how social justice works in a variety of educational settings. We altered our approach to data collection and doctoral supervision. In so doing, we were able to maintain consistency for our students and develop a closer bond with our faculty colleagues.

Artificial intelligence in education (AIEd) is a fast-growing field of research. In previous work, we described efforts to explore the possible futures of AIEd by identifying key variables and their future prospects. This paper re-examines our discussions on the governance of data and the role of students and teachers by considering the implications of (1) a recent case related to the General Data Protection Regulation (GDPR) and (2) the release of ChatGPT, a generative AI model capable to producing 'human-like' text. These events raise questions for the future of AIEd and the underlying function of assessment, and highlight the importance of active student participation in the integration of AI in education. [This article has been presented in the 5th International Open & Distance Learning Conference-IODL 2022.]

Educational data mining has allowed for large improvements in educational outcomes and understanding of educational processes. However, there remains a constant tension between educational data mining advances and protecting student privacy while using educational datasets. Publicly available datasets have facilitated numerous research projects while striving to preserve student privacy via strict anonymization protocols (e.g., k-anonymity); however, little is known about the relationship between anonymization and utility of educational datasets for downstream educational data mining tasks, nor how anonymization processes might be improved for such tasks. We provide a framework for strictly anonymizing educational datasets with a focus on improving downstream performance in common tasks such as student outcome prediction. We evaluate our anonymization framework on five diverse educational datasets with machine learning-based downstream task examples to demonstrate both the effect of anonymization and our means to improve it. Our method improves downstream machine learning accuracy versus baseline data anonymization by 30.59%, on average, by guiding the anonymization process toward strategies that anonymize the least important information while leaving the most valuable information intact.

The rapid development of education informatization has accumulated a large amount of data for learning analytics, and adopting educational data mining to find new patterns of data, develop new algorithms and models, and apply known predictive models to the teaching system to improve learning is the challenge and vision of the education field in the era of big data. Learning intervention, as a core concept of learning analytics, refers to the purposeful and planned adoption of direct or indirect strategies or behaviors based on tracking learning behaviors and integrating information about learners' characteristics to give learners personalized guidance and assistance in order to help learners break through the status quo of learning difficulties and improve their learning abilities, so as to achieve tailored teaching. In this study, data mining was conducted on the performance records of students on math problems in an online learning system, and a learning intervention suggestion prediction model was constructed on the basis of decision tree algorithm using Python, with a view to understanding the effectiveness, willingness, style, and other characteristics of the learners' online learning through the analysis results, providing personalized guidance to students, and enabling teachers to intervene with at-risk students and successfully complete the teaching goals. It was found that the most significant impact of the learning intervention advice provided to learners was the number of hints they sought during the learning process, and that learners who needed to be "intervened" or "monitored" could be categorized into two groups: independent inefficient and dependent inefficient according to the model. Therefore, teachers or adaptive learning systems should intervene in a timely and appropriate way for different types of learning crisis groups to solve the problems of poor learning performance, insufficient commitment to learning, poor learning habits, low participation in learning, low self-efficacy and other problems of learners in different learning scenarios.

With the aim to provide teachers with more specific, frequent, and actionable feedback about their teaching, we explore how Large Language Models (LLMs) can be used to estimate "Instructional Support" domain scores of the CLassroom Assessment Scoring System (CLASS), a widely used observation protocol. We design a machine learning architecture that uses either zero-shot prompting of Meta's Llama2, and/or a classic Bag of Words (BoW) model, to classify individual utterances of teachers' speech (transcribed automatically using OpenAI's Whisper) for the presence of Instructional Support. Then, these utterance-level judgments are aggregated over a 15-min observation session to estimate a global CLASS score. Experiments on two CLASS-coded datasets of toddler and pre-kindergarten classrooms indicate that (1) automatic CLASS Instructional Support estimation accuracy using the proposed method (Pearson R up to 0.48) approaches human inter-rater reliability (up to R = 0.55); (2) LLMs generally yield slightly greater accuracy than BoW for this task, though the best models often combined features extracted from both LLM and BoW; and (3) for classifying individual utterances, there is still room for improvement of automated methods compared to human-level judgments. Finally, (4) we illustrate how the model's outputs can be visualized at the utterance level to provide teachers with explainable feedback on which utterances were most positively or negatively correlated with specific CLASS dimensions.

LearnSphere is a web-based data infrastructure designed to transform scientific discovery and innovation in education. It supports learning researchers in addressing a broad range of issues including cognitive, social, and motivational factors in learning, educational content analysis, and educational technology innovation. LearnSphere integrates previously separate educational data and analytic resources developed by participating institutions. The web-based workflow authoring tool, Tigris, allows technical users to contribute sophisticated analytic methods, and learning researchers can adapt and apply those methods using graphical user interfaces, importantly, without additional programming. As part of our use-driven design of LearnSphere, we built a community through workshops and summer schools on educational data mining. Researchers interested in particular student levels or content domains can find student data from elementary through higher-education and across a wide variety of course content such as math, science, computing, and language learning. LearnSphere has facilitated many discoveries about learning, including the importance of active over passive learning activities and the positive association of quality discussion board posts with learning outcomes. LearnSphere also supports research reproducibility, replicability, traceability, and transparency as researchers can share their data and analytic methods along with links to research papers. We demonstrate the capabilities of LearnSphere through a series of case studies that illustrate how analytic components can be combined into research workflow combinations that can be developed and shared. We also show how open web-accessible analytics drive the creation of common formats to streamline repeated analytics and facilitate wider and more flexible dissemination of analytic tool kits.