Search

Collaboration has garnered global attention as an important skill for the 21st century. While researchers have been doing work on collaboration for nearly a century, many of the questions that the field is investigating overlook the need for students to learn how to read and respond to different collaborative settings. Existing research focuses on chronicling the various factors that predict the effectiveness of a collaborative experience, or on changing user behaviour in the moment. These are worthwhile research endeavours for developing our theoretical understanding of collaboration. However, there is also a need to centre student perceptions and experiences with collaboration as an important area of inquiry. Based on a survey of 131 university students, we find that student collaboration-related concerns can be represented across seven different categories or dimensions: Climate, Compatibility, Communication, Conflict, Context, Contribution, and Constructive. These categories extend prior research on collaboration and can help the field ensure that future collaboration analytics tools are designed to support the ways that students think about and utilize collaboration. Finally, we describe our instantiation of many of these dimensions in our collaborative analytics tool, BLINC, and suggest that these seven dimensions can be instructive for re-orienting the Multimodal Learning Analytics (MMLA) and collaboration analytics communities.

Multimodal learning analytics (MMLA) has increasingly been a topic of discussion within the learning analytics community. The Society of Learning Analytics Research is home to the CrossMMLA Special Interest Group and regularly hosts workshops on MMLA during the Learning Analytics Summer Institute (LASI). In this paper, we articulate a set of 12 commitments that we believe are critical for creating effective MMLA innovations. Moreover, as MMLA grows in use, it is important to articulate a set of core commitments that can help guide both MMLA researchers and the broader learning analytics community. The commitments that we describe are deeply rooted in the origins of MMLA and also reflect the ways that MMLA has evolved over the past 10 years. We organize the 12 commitments in terms of (i) data collection, (ii) analysis and inference, and (iii) feedback and data dissemination and argue why these commitments are important for conducting ethical, high-quality MMLA research. Furthermore, in using the language of commitments, we emphasize opportunities for MMLA research to align with established qualitative research methodologies and important concerns from critical studies.

Two nascent lines of inquiry in the Learning Sciences are contributing to research and development of interactive digital resources for STEM education. One is embodied design, a research program to create theoretically driven and empirically validated technological learning environments where students ground STEM concepts in new perceptual capacity they develop through solving motor-control problems. The other is multimodal learning analytics, a methodological approach to investigating learning processes through gathering, analyzing, triangulating, and presenting data from multiple measures of students’ actions and sensations. This special issue looks at a set of articles reporting on pioneering efforts to coordinate these parallel lines of inquiry into a theoretically coherent research program informing an integrated design framework. The following editorial frames and motivates these research efforts, surveys the set of papers, and speculates on possible futures for the learning analytics of embodied design.

Background and Context: Making is celebrated for bringing exciting tools and learning opportunities to non-traditional designers. However, people with disabilities may find themselves excluded from many making activities and makerspaces. This exclusion is present in making and computer science more broadly. Objective: We describe a university course that helps broaden their awareness of accessibility in computing and promote accessible making solutions. The course engages students in critical examination of making and allows them to instantiate their learning by designing accessible interfaces and experiences. We study the design of the course and its impacts on students. Method: We use techniques from grounded theory to analyze data from surveys, projects, and case studies to elucidate the need and the impact of this experience. Findings: The course filled an important need for students and people with disabilities. By applying a critical disability lens to making, participants developed expansive views of making, both in terms of what "counts" as making and who can participate in it. Implications: Courses on accessibility address important societal and individual needs that are currently not met by CS curricula. Courses that address these needs should include critical discussions of the domain in question and involve various types of community partnerships. Including these course elements can expand the course's impact, lead to better project designs, and change perceptions of what is valuable in computing experiences.

Purpose: This paper aims to compare two types of prompts, encouraging participants to think about real-world examples or engineering principles to show how these two approaches can result in vastly different design practices. Design/methodology/approach: Two studies (N = 20, N = 40) examine the impact of two different prompts. Non-expert students, from high school and university, completed a hands-on, engineering design task in pairs. Half were prompted to ideate using real-world examples, while the other half were prompted to ideate using engineering principles. The findings are based on human coding and artifact analyses. Findings: In both studies, and across multiple measures, students in the principle-based condition performed better than students in the example-based condition. Research limitations/implications: A seemingly small difference in how students are prompted or encouraged to approach a problem can have a significant impact on their experience. The findings also suggest that leveraging engineering principles, even when those principles are only loosely formed, can be effective even for non-experts. Finally, the findings motivate identifying student reasoning strategies over time as a potential means for assessment in Makerspaces. Practical implications: Encouraging makers to think about different ways for approaching problems can be an important way to help them succeed. It may also be a useful way to chronicle their learning pathway. Originality/value: To the author's knowledge, explicitly looking at ideation strategies has not been widely discussed within the Maker community as a way to support learners, or as a way to evaluate learning.

New high-frequency multimodal data collection technologies and machine learning analysis techniques could offer new insights into learning, especially when students have the opportunity to generate unique, personalized artifacts, such as computer programs, robots, and solutions engineering challenges. To date most of the work on learning analytics and educational data mining has been focused on online courses and cognitive tutors, both of which provide a high degree of structure to the tasks, and are restricted to interactions that occur in front of a computer screen. In this paper, we argue that multimodal learning analytics can offer new insights into student learning trajectories in more complex and open-ended learning environments. We present several examples of this work and its educational applications.

Background and Context: Sports and technology are often pitted as being at odds with one another. While there are several educational activities that make reference to sports we seldom see sports used as an authentic context for learning computing. Objective: We describe the design of Data in Motion, a curriculum that considers the bi-directional opportunities for sports to improve learning of STEM and for STEM to help improve participants' athletic performance. Method: We implement Data in Motion as a five-day summer camp with 33 participants, grades 2-6. We observe the ways that the experience changes students' perceptions of the connection between sports and technology through student surveys, observations and artifact analyses. Findings: Across the pool of participants, we saw significant changes in the ways that students conceptualized the connection between technology and athletic performance. We also saw students who are not interested in sports demonstrate high engagement in the experience. Implications: Practice-linked learning, specifically in the context of sports and technology, is a generative space for students to authentically explore interests in both disciplines. Researchers and practitioners should consider this intersection as a potential space to broaden modes of participation in computer science.

Learning analytics and educational data mining are introducing a number of new techniques and frameworks for studying learning. The scalability and complexity of these novel techniques has afforded new ways for enacting education research and has helped scholars gain new insights into human cognition and learning. Nonetheless, there remain some domains for which pure computational analysis is currently infeasible. One such area, which is particularly important today, is open-ended, hands-on, engineering design tasks. These open-ended tasks are becoming increasingly prevalent in both K-12 and post-secondary learning institutions, as educators are adopting this approach in order to teach students real-world science and engineering skills (e.g., the "Maker Movement"). This paper highlights findings from a combined human-computer analysis of students as they complete a short engineering design task. The study uncovers novel insights and serves to advance the field's understanding of engineering design patterns. More specifically, this paper uses machine learning on hand-coded video data to identify general patterns in engineering design and develop a fine-grained representation of how experience relates to engineering practices. Finally, the paper concludes with ideas on how the specific findings from this study can be used to improve engineering education and the nascent field of "making" and digital fabrication in education. We also discuss how human-computer collaborative analyses can grow the learning analytics community and make learning analytics more central to education research.

This paper presents three multimodal learning analytic approaches from a hands-on learning activity. We use video, audio, gesture and bio-physiology data from a two-condition study (N = 20), to identify correlations between the multimodal data, experimental condition, and two learning outcomes: design quality and learning. The three approaches incorporate: 1) human-annotated coding of video data, 2) automated coding of gesture, audio and bio-physiological data and, 3) concatenated human-annotated and automatically annotated data. Within each analysis we employ the same machine learning and sequence mining techniques. Ultimately we find that each approach provides different affordances depending on the similarity metric and the dependent variable. For example, the analysis based on human-annotated data found strong correlations among multimodal behaviors, experimental condition, success and learning, when we relaxed constraints on temporal similarity. The second approach performed well when comparing students' multimodal behaviors as a time series, but was less effective using the temporally relaxed similarity metric. The take-away is that there are several strategies for doing multimodal learning analytics, and that many of these approaches can provide a meaningful glimpse into a complex data set, glimpses that may be difficult to identify using traditional approaches.

"Making" represents an increasingly popular label for describing a form of engineering design. While making is growing in popularity, there are still open questions about the strategies that students are using in these activities. Assessing and improving learning in making/ engineering design contexts require that we have a better understanding of where students' ideas are coming from and a better way to characterize student progress in open-ended learning environments. In this article, we use a qualitative analysis of students' responses (N = 13) in order to identify the origins of their ideas. Four strategies emerged from this analysis: unexplained reasoning; materials-based reasoning; example-based reasoning; and principle-based reasoning. We examine key characteristics of each strategy and how each strategy relates to learning and expertise through in-depth case studies. Furthermore, we identify how these four strategies are a complement to prior work on analogical problem solving and creativity, and offer a number of unique contributions that are particularly relevant for engineering education. Finally, we include two coding schemes that can be used to classify students' responses. Studying reasoning strategies in this way is a fruitful means for characterizing student learning in complex learning environments. Moreover, understanding reasoning strategies impacts the nature of student' teacher discussions and informs how to help students progress most effectively.

New high-frequency, automated data collection and analysis algorithms could offer new insights into complex learning processes, especially for tasks in which students have opportunities to generate unique open-ended artifacts such as computer programs. These approaches should be particularly useful because the need for scalable project-based and student-centered learning is growing considerably. In this article, we present studies focused on how students learn computer programming, based on data drawn from 154,000 code snapshots of computer programs under development by approximately 370 students enrolled in an introductory undergraduate programming course. We use methods from machine learning to discover patterns in the data and try to predict final exam grades. We begin with a set of exploratory experiments that use fully automated techniques to investigate how much students change their programming behavior throughout all assignments in the course. The results show that students' change in programming patterns is only weakly predictive of course performance. We subsequently hone in on 1 single assignment, trying to map students' learning process and trajectories and automatically identify productive and unproductive (sink) states within these trajectories. Results show that our process-based metric has better predictive power for final exams than the midterm grades. We conclude with recommendations about the use of such methods for assessment, real-time feedback, and course improvement.