Self-regulated Learning Path Mining and Feedback Based on Learning Analytics
Self-regulated learning is the necessary way to acquire knowledge in the digital age. In order to provide learners with personalized support services to enhance their self-regulated learning performance and learning ability， this study collects and sorts out the learning process data in the Moodle platform， uses SSAS sequence analysis and clustering analysis， SPSS hierarchical cluster analysis methods， mines learners’ learning path clustered by learning styles， academic performance and learning preferences， analyzes the path characteristics of different types of learners. On this basis， provides feedback for learners ，such as the feedback of knowledge map， learning paths and learning results. Finally， the experimental method， empirical research questionnaires and interview method are used to test the effect of learning path mining and corresponding feedback from three aspects: academic performance， metacognition， learning path. The results show that self-regulated learning path mining and corresponding feedback based on learning analysis can optimize the learning effect and learning process， promote the development of learning ability.
|關鍵詞||学习分析、学习路径、反馈、自我调节学习、Learning Analytics、Learning Path、Feedback、Self-regulated Learning、CSSCI|