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

Abstract

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.