Modeling Micro-Interactions in Self-Regulated Learning: a Data-Driven Methodology

Abstract We explore whether interactive navigational behaviours can be used as a reliable and effective source to measure the progress, achievement, and engagement of a learning process. To do this, we propose a data-driven methodology involving sequential pattern mining and thematic analysis of the low-level navigational interactions. We applied the method on an online learning platform which involved 193 students resulting in six interactive behaviours that are significantly associated with learner achievement including exploration of the first week’s materials and exploration of the forum. The value of including these behaviours in predictive models increased their explainability by 10% and accounted for an overall explainability of 82%. Performance evaluations of the models indicate 91-95% accuracy in identifying low-achieving students. Other relevant findings indicate a strong association between the reduction of the behaviours over time and student achievement. This suggests a relationship between student interface learnability and achievement: achievers become more efficient at using the functionalities of an online learning platform. These findings can provide context to learning progress and theoretical foundations of interventions against unhelpful learning behaviours.