A Self-Regulated Learning System to Support Adaptive Scaffolding in Hypermedia-based Learning Environments

A Hypermedia-based Learning Environment (HLE) has shown potential in helping students improve their learning performance in terms of complicated subjects and skills; however, most students find it difficult to learn well in this kind of Open-Ended Learning Environments (OELE) due to a lack of Self-Regulated Learning (SRL) abilities. Manually adaptive scaffolding is labor-intensive and time-consuming, and Intelligent Tutoring Systems focus on the process of adaptive learning content and paths, not the SRL. Therefore, this paper proposes a Self-Regulated Learning System with Rule-based Learning Diagnostic Scheme (SRLS-RLDS) to automatically support adaptive scaffoldings for students in an HLE/OELE, where a rule-based approach and concept ontology is used to model teachers' diagnostic knowledge to help students regulate their learning. The proposed SRLS-RLDS was applied to a case of software learning, and the experimental results showed that students who studied with SRLS-RLDS adaptive scaffoldings had significantly higher post-test scores than those who studied without adaptive scaffoldings. Moreover, all students agreed that the proposed SRLS-RLDS scheme can effectively help them concentrate on learning content and to better understand the domain knowledge in their self-regulated learning processes.