Combining University Student Self-Regulated Learning Indicators and Engagement with Online Learning Events to Predict Academic Performance

Self-regulated learning theories are used to understand the reasons for different levels of university student academic performance. Similarly, learning analytics research proposes the combination of detailed data traces derived from technology-mediated tasks with a variety of algorithms to predict student academic performance. The former approach is designed to provide meaningful pedagogical guidance, while the latter is designed to identify event patterns and relations that can be translated into actionable remediation. The benefits of both approaches have motivated this study to investigate if a combination of the self-report data and data arising from an observation of the engagement of students with online learning events offers a deeper understanding and explanation of why some students achieve relatively higher levels of academic performance. In this paper we explore how to combine data about self-regulated learning skills with observable measures of online activity in a blended learning course to increase predictive capabilities of student academic performance for the purposes of informing teaching and task design. A case study in a course with 145 students showed that the variation of the students' final score for their course is better explained when factors from both approaches are considered. The results point to the potential of adopting a combined use of self-report and observed data to gain a more comprehensive understanding of successful university student learning.