The ability to sustain engagement and recover from setbacks (i.e., resilience)—is fundamental for learning. When resilience weakens, students are at risk of disengagement and may drop out and miss on opportunities. Therefore, predicting disengagement long before it happens during the window of hope is important. In this article, we test whether early warning signals of resilience loss, grounded in the concept of critical slowing down (CSD) can forecast disengagement before dropping out. CSD has been widely observed across ecological, climate, and neural systems, where it precedes tipping points into catastrophic failure (dropping out in our case). Using 1.67 million practice attempts from 9,401 students who used a digital math learning environment, we computed CSD indicators: autocorrelation, return rate, variance, skewness, kurtosis, and coefficient of variation. We found that 88.2% of students exhibited CSD signals prior to disengagement, with warnings clustering late in activity and before practice ceased (dropping out). Our results provide the first evidence of CSD in education, suggesting that universal resilience dynamics also govern social systems such as human learning. These findings offer a practical indicator for early detection of vulnerability and supporting learners across different applications and contexts long before critical events happen. Most importantly, CSD indicators arise universally, independent of the mechanisms that generate the data, offering new opportunities for portability across contexts, data types, and learning environments.

Escape rooms have evolved from recreational activities to engaging educational tools, combining storytelling, puzzlesolving, and teamwork. Despite their popularity, research on escape rooms remains highly decentralized with no clear focus or pathway. To shed some light on this growing field, this study analyzes 1,051 published articles on escape rooms using natural language processing, specifically keyword analysis and structured topic modeling. Our study addresses four key research questions related to (1) commonly used phrases, (2) research topics, (3) the evolution of these topics, and (4) their interconnections. We identified 24 distinct topics categorized into design and development, field of application, participants, and technology. The analysis reveals an almost exclusive focus on educational applications (>90%), particularly in healthcare and STEM education, highlighting soft skills and practical knowledge development. Based on our findings, we provide a research agenda where we highlight future research opportunities which include expanding research methods, incorporating generative artificial intelligence and easing the barriers to adoption for teachers.

This paper presents an explainable AI (XAI) education tool designed for K-12 classrooms, particularly for students aged 11-16. The tool was designed for interventions on the fundamental processes behind social media platforms, focusing on four AI- and data-driven core concepts: data collection, user profiling, engagement metrics, and recommendation algorithms. An Instagram-like interface and a monitoring tool for explaining the data-driven processes make these complex ideas accessible and engaging for young learners. The tool provides hands-on experiments and real-time visualizations, illustrating how user actions influence their personal experience on the platform as well as the experience of others. This approach seeks to enhance learners' data agency, AI literacy, and sensitivity to AI ethics. The paper includes a case example from 12 two-hour test sessions involving 209 children, using learning analytics to demonstrate how they navigated their social media feeds and the browsing patterns that emerged.

The rapid adoption of ChatGPT and other large language models (LLMs) in education has created new opportunities for human-AI collaboration research, e.g., studying interactions, automating support or implementing novel ways of assessment. However, existing methods for retrieving ChatGPT conversation data -either through OpenAI's API or manual transcription-are limited by technical, financial, and scalability constraints. This paper introduces chatGPTscrapeR, an open-source R package and Shiny web application that automates the extraction of ChatGPT conversation data from URLs. Thus, it enables researchers and educators to efficiently retrieve, organize, and subsequently analyze interaction logs, and their metadata. The retrieved data are ready to be assessed if they are part of an assignment or analyzed using different methods. In all such cases, automating the retrieval of human-AI interactions is instrumental for an efficient analysis of such interactions and for creating modern AI-enabled learning systems.

While research on social network analysis is abundant and less frequently so temporal network analysis, research that uses inferential temporal network methods is barely existent. This paper aims to fill this gap by conducting a comparative analysis of temporal networks and inferential longitudinal network methods in the context of learner interactions in Massive Open Online Courses (MOOCs). We focus on three prominent methods: Temporal Network Analysis (TNA), Temporal Exponential Random Graph Models (TERGM) and Simulation Investigation for Empirical Network Analysis (SIENA). Using a five-week Nature Education MOOC as a case study, we compared the features, metrics of each method as well as their understanding of using network to analyze learner interactions. TNA focuses on describing and visualizing temporal changes in network structure, while TERGM and SIENA view networks as evolving systems influenced by individual behaviors and structural dependencies. TERGM treats network changes as a joint of random processes, while SIENA emphasizes the agency of learners and analyzes continuous network evolution. The findings provide guidelines for researchers and educators to select appropriate network analysis methods for temporal studies in educational contexts.

It stands to reason that if we want to offer "personalized" education, our methods should be designed to capture the person and the intraindividual processes. However, an idiographic approach that investigates within-person processes and provides insights on the person has been so far lagging. We conducted a scoping review to explore how the idiographic approach has been applied in educational research (i.e., what methods, topics, data, and statistical approaches). We found that person-specific analysis has mostly been used to investigate education psychology constructs. In addition,Except for a few exceptions in learning analytics, many idiographic studies have employed basic statistical techniques, whereas advanced statistical methods have been applied only recently. Therefore, considering the recent development of educational data science, the potential of idiographic methodology needs to be explored further.

Research on academic emotions has explored different granularities that range from a full program to a single task. Yet, most of the existing research stems from cross-sectional studies. While immensely useful, lacking a temporal depth obfuscates the process of emotions into a flat process. To fill this gap, this study takes a process-oriented approach to study the momentary changes in academic emotions as they unfold in time into phases, changes, and successions of sequences during two lectures. We use intensive longitudinal data from 104 students attending a German University in the form of ecological momentary surveys. We rely on mixture models to cluster the data into states, use sequence analysis to map the longitudinal unfolding and mixture hidden Markov models to answer why certain longitudinal patterns emerge. Our findings point to differences among students in their reactions to contextual variables, yet, such reactions are relatively stable within students. In other words, students may have different emotional profiles, but these emotional profiles are surprisingly stable across time and contexts.

While learning analytics dashboards (LADs) are the most common form of LA intervention, there is limited evidence regarding their impact on students’ learning outcomes. This systematic review synthesizes the findings of 38 research studies to investigate the impact of LADs on students' learning outcomes, encompassing achievement, participation, motivation, and attitudes. As we currently stand, there is no evidence to support the conclusion that LADs have lived up to the promise of improving academic achievement. Most studies reported negligible or small effects, with limited evidence from well-powered controlled experiments. Many studies merely compared users and non-users of LADs, confounding the dashboard effect with student engagement levels. Similarly, the impact of LADs on motivation and attitudes appeared modest, with only a few exceptions demonstrating significant effects. Small sample sizes in these studies highlight the need for larger-scale investigations to validate these findings. Notably, LADs showed a relatively substantial impact on student participation. Several studies reported medium to large effect sizes, suggesting that LADs can promote engagement and interaction in online learning environments. However, methodological shortcomings, such as reliance on traditional evaluation methods, self-selection bias, the assumption that access equates to usage, and a lack of standardized assessment tools, emerged as recurring issues. To advance the research line for LADs, researchers should use rigorous assessment methods and establish clear standards for evaluating learning constructs. Such efforts will advance our understanding of the potential of LADs to enhance learning outcomes and provide valuable insights for educators and researchers alike.

IEEE/ASEE Frontiers in Education turned 50 at the 2020 virtual conference in Uppsala, Sweden. This paper presents an historical retrospective on the first 50 years of the conference from a scientometric perspective. That is to say, we explore the evolution of the conference in terms of prolific authors, communities of co-authorship, clusters of topics, and internationalization, as the conference transcended its largely provincial US roots to become a truly international forum through which to explore the frontiers of educational research and practice. The paper demonstrates the significance of FIE for a core of 30% repeat authors, many of whom have been members of the community and regular contributors for more than 20 years. It also demonstrates that internal citation rates are low, and that the co-authoring networks remain strongly dominated by clusters around highly prolific authors from a few well known US institutions. We conclude that FIE has truly come of age as an international venue for publishing high quality research and practice papers, while at the same time urging members of the community to be aware of prior work published at FIE, and to consider using it more actively as a foundation for future advances in the field.

Idiographic methods have emerged as a way to examine individual behavior by using several data points from each subject to create person-specific insights. In the field of learning analytics, such methods could overcome the limitations of cross-sectional group-level data that may fail to capture the dynamic processes that unfold within each individual learner and less likely to offer relevant personalized learning or support. In this study, we provide a definition of idiographic learning analytics and we explore the possible potentials of this method to zoom in on the fine-grained dynamics of a single student. Specifically, we make use of Gaussian Graphical Models -an emerging trend in network science- to analyze a single student's dispositions and devise insights specific to him/her. Our findings offer a proof of concept of the potential of this novel method in revealing personalized valuable insights about students' self-regulation. While our specific findings apply to a single student, our method applies to every student regardless of context.

The momentum around computational thinking (CT) has kindled a rising wave of research initiatives and scholarly contributions seeking to capitalize on the opportunities that CT could bring. A number of literature reviews have showed a vibrant community of practitioners and a growing number of publications. However, the history and evolution of the emerging research topic, the milestone publications that have shaped its directions, and the timeline of the important developments may be better told through a quantitative, scientometric narrative. This article presents a bibliometric analysis of the drivers of the CT topic, as well as its main themes of research, international collaborations, influential authors, and seminal publications, and how authors and publications have influenced one another. The metadata of 1,874 documents were retrieved from the Scopus database using the keyword “computational thinking.” The results show that CT research has been US-centric from the start, and continues to be dominated by US researchers both in volume and impact. International collaboration is relatively low, but clusters of joint research are found between, for example, a number of Nordic countries, lusophone- and hispanophone countries, and central European countries. The results show that CT features the computing’s traditional tripartite disciplinary structure (design, modeling, and theory), a distinct emphasis on programming, and a strong pedagogical and educational backdrop including constructionism, self-efficacy, motivation, and teacher training.

Previous work in learning analytics have been fruitful in shedding lights on collaborative learning environments, such work has provided insights and recommendations that helped improve the collaborative process in computer-mediated learning environments. Given the importance of social interactions and their influence on learning (e.g., in determining academic growth, perseverance in the course and persistence). In this study, we look at both learning and social networks, what factors they share, how they impact or influence learning, and what influences the formation of these networks. Our results show similarities and differences between both networks such as: interactions in the social network predict those in the learning network, however, only centrality measures in the learning network correlate with performance, probably due to the selective nature of replies and interactions in the learning network.

There has been significant efforts in studying collaborative and social learning using aggregate networks. Such efforts have demonstrated the worth of the approach by providing insights about the interactions, student and teacher roles, and predictability of performance. However, using an aggregated network discounts the fine resolution of temporal interactions. By doing so, we might overlook the regularities/irregularities of students' interactions, the process of learning regulation, and how and when different actors influence each other. Thus, compressing a complex temporal process such as learning may be oversimplifying and reductionist. Through a temporal network analysis of 54 students interactions (in total 3134 interactions) in an online medical education course, this study contributes with a methodological approach to building, visualizing and quantitatively analyzing temporal networks, that could help educational practitioners understand important temporal aspects of collaborative learning that might need attention and action. Furthermore, the analysis conducted emphasize the importance of considering the time characteristics of the data that should be used when attempting to, for instance, implement early predictions of performance and early detection of students and groups that need support and attention.

The master thesis is the last formal step in most universities around the world. However, all students do not finish their master thesis. Thus, it is reasonable to assume that the non-completion of the master thesis should be viewed as a substantial problem that requires serious attention and proactive planning. This learning analytics study aims to understand better factors that influence completion and non-completion of master thesis projects. More specifically, we ask: which student and supervisor factors influence completion and non-completion of master thesis? Can we predict completion and non-completion of master thesis using such variables in order to optimise the matching of supervisors and students? To answer the research questions, we extracted data about supervisors and students from two thesis management systems which record large amounts of data related to the thesis process. The sample used was 755 master thesis projects supervised by 109 teachers. By applying traditional statistical methods (descriptive statistics, correlation tests and independent sample t-tests), as well as machine learning algorithms, we identify five central factors that can accurately predict master thesis completion and non-completion. Besides the identified predictors that explain master thesis completion and non-completion, this study contributes to demonstrating how educational data and learning analytics can produce actionable data-driven insights. In this case, insights that can be utilised to inform and optimise how supervisors and students are matched and to stimulate targeted training and capacity building of supervisors.

Effective collaborative learning is rarely a spontaneous phenomenon. In fact, it requires that a set of conditions are met. Among these central conditions are group formation, size and interaction dynamics. While previous research has demonstrated that size might have detrimental effects on collaborative learning, few have examined how social dynamics develop depending on group size. This learning analytics paper reports on a study that asks: How is group size affecting social dynamics and performance of collaborating students? In contrast to previous research that was mainly qualitative and assessed a limited sample size, our study included 23,979 interactions from 20 courses, 114 groups and 974 students and the group size ranged from 7 to 15 in the context of online problem-based learning. To capture the social dynamics, we applied social network analysis for the study of how group size affects collaborative learning. In general, we conclude that larger groups are associated with decreased performance of individual students, poorer and less diverse social interactions. A high group size led to a less cohesive group, with less efficient communication and less information exchange among members. Large groups may facilitate isolation and inactivity of some students, which is contrary to what collaborative learning is about.