From procrastination to engagement? An experimental exploration of the effects of an adaptive virtual assistant on self-regulation in online learning

Abstract

Compared to traditional classroom learning, success in online learning tends to depend more on the learner’s skill to self-regulate. Self-regulation is a complex meta-cognitive skill set that can be acquired. This study explores the effectiveness of a virtual learning assistant in terms of (a) developmental, (b) general compensatory, and (c) differential compensatory effects on learners’ self-regulatory skills in a sample of N = 157 online learners using an experimental intervention-control group design. Methods employed include behavioural trace data as well as self-reporting measures. Participants provided demographic information and responded to a 24-item self-regulation questionnaire and a 20-item personality trait questionnaire. Results indicate that the adaptive assistance did not lead to substantial developmental shifts as captured in learners’ perceived levels of self-regulation. However, various patterns of behavioural changes emerged in response to the intervention. This suggests that the virtual learning assistant has the potential to help online learners effectively compensate for deficits (in contrast to developmental shifts) in self-regulatory skills that might not yet have been developed.

Keywords

• MOOC
• Self-regulated learning
• Developmental vs compensatory shifts
• Self ratings
• Personality
• Behavior traces