Analysing Structured Learning Behaviour in Massive Open Online Courses (MOOCs): An Approach Based on Process Mining and Clustering
Antoine van den Beemt, Eindhoven School of Education, Eindhoven University of Technology, The Netherlands ; Joos Buijs, Eindhoven University of Technology ; Wil van der Aalst, RWTH Aachen University, Germany
IRRODL Volume 19, Number 5, ISSN 1492-3831 Publisher: Athabasca University Press
The increasing use of digital systems to support learning leads to a growth in data regarding both learning processes and related contexts. Learning Analytics offers critical insights from these data, through an innovative combination of tools and techniques. In this paper, we explore students’ activities in a MOOC from the perspective of personal constructivism, which we operationalized as a combination of learning behaviour and learning progress. This study considers students’ data analyzed as per the MOOC Process Mining: Data Science in Action. We explore the relation between learning behaviour and learning progress in MOOCs, with the purpose to gain insight into how passing and failing students distribute their activities differently along the course weeks, rather than predict students' grades from their activities. Commonly-studied aggregated counts of activities, specific course item counts, and order of activities were examined with cluster analyses, means analyses, and process mining techniques. We found four meaningful clusters of students, each representing specific behaviour ranging from only starting to fully completing the course. Process mining techniques show that successful students exhibit a more steady learning behaviour. However, this behaviour is much more related to actually watching videos than to the timing of activities. The results offer guidance for teachers.
van den Beemt, A., Buijs, J. & van der Aalst, W. (2018). Analysing Structured Learning Behaviour in Massive Open Online Courses (MOOCs): An Approach Based on Process Mining and Clustering. The International Review of Research in Open and Distributed Learning, 19(5),. Athabasca University Press.