Background: When learning causal relations, completing causal diagrams enhances students' comprehension judgements to some extent. To potentially boost this effect, advances in natural language processing (NLP) enable real-time formative feedback based on the automated assessment of students' diagrams, which can involve the correctness of both the…

In this study, we explore the application of process mining techniques on assessment log data to explore problem-solving strategies in Algebra. By analyzing sequences of student activities, we demonstrate the significant potential of process mining in identifying problem-solving strategies that lead to successful and unsuccessful outcomes. Our…

The availability of large-scale learning data presents unprecedented opportunities for investigating student learning processes. However, it is challenging for instructors to fully make sense of this data and effectively support their teaching practices. This study introduces LearningViz, an interactive learning analytics dashboard to help…

This systematic literature review investigates the fairness of machine learning algorithms in educational settings, focusing on recent studies and their proposed solutions to address biases. Applications analyzed include student dropout prediction, performance prediction, forum post classification, and recommender systems. We identify common…

Randomized A/B tests within online learning platforms enable us to draw unbiased causal estimators. However, precise estimates of treatment effects can be challenging due to minimal participation, resulting in underpowered A/B tests. Recent advancements indicate that leveraging auxiliary information from detailed logs and employing design-based…

Understanding students' privacy concerns is an essential first step toward effective privacy-enhancing practices in learning analytics (LA). In this study, we develop and validate a model to explore the students' privacy concerns (SPICE) regarding LA practice in higher education. The SPICE model considers "privacy concerns" as a central…

Student engagement is consistently identified as a key predictor of learner outcomes within the online learning environment. However, there is limited guidance about using proactive strategies to improve engagement for low and non-engaged students: for example by specifically employing course learning analytics (CLA) and nudging strategies in…

Learning analytics dashboards have been developed to facilitate teacher guidance in computer-supported collaborative learning (CSCL). As yet, little is known about how teachers interpret dashboard information to facilitate guidance in their teaching practice. This study examined teachers' behavior patterns in interpreting information from…

Lecture capture is popular within Higher Education, but previous research suggests that students do not always optimally select content to review, nor do they make the most of specific functions. In the current study conducted in the 2019/20 academic year, we used a repeated-measures crossover design to establish the effects of transcripts with…

In this paper, an empirical comparison of three state-of-the-art classifier methods (artificial immune recognition systems, Lazy-K Star, and random tree) to predict teachers' ability to adapt in a classroom environment is carried out. Two educational databases are used for this task. First, measures collected in an academic context, especially…

This commentary discusses how research approaches from Cognitive Network Science can be of relevance to research in the field of Learning Analytics, with a focus on modelling the knowledge representations of learners and students as a network of interrelated concepts. After providing a brief overview of research in Cognitive Network Science, I…

E-learning students have a tendency to get demotivated and easily dropout from online courses. Refining the learners' involvement and reducing dropout rates in these e-learning based scenarios is the main drive of this study. This study also shares the results obtained and crafts a comparison with new and emerging commercial solutions. In a…

Learning activities are at the core of every educational design effort. Designing learning activities is a process that benefits from reflecting on previous runs of those activities. One way to measure the behaviour and effects of design choices is to use learning analytics (LA). The challenge, however, lies in the unavailability of an…

Learning Analytics (LA) systems can offer new insights into learners' behaviours through analysis of multiple data streams. There remains however a dearth of research about how LA interfaces can enable effective communication of educationally meaningful insights to teachers and learners. This highlights the need for a participatory, horizontal…

In this contribution to the Platform Studies in Education symposium, Luci Pangrazio, Amy Stornaiuolo, T. Philip Nichols, Antero Garcia, and Thomas M. Philip explore how digital platforms can be used to build knowledge and understanding of datafication processes among teachers and students. The essay responds to the turn toward data-driven teaching…