The interactions among all members of an online learning community significantly impact collaborative reflection (co-reflection). Although the relationship between learners’ roles and co-reflection levels has been explored by previous researchers, it remains unclear when and with whom learners at different co-reflection levels tend to interact. This study adopted multiple methods to examine the interaction patterns of diverse roles among learners with different co-reflection levels based on 11,912 posts. First, the deep learning technique was applied to assess learners’ co-reflection levels. Then, a social network analysis (SNA) was conducted to identify the emergent roles of learners. Furthermore, a lag sequence analysis (LSA) was employed to reveal the interaction patterns of the emergent roles among learners with different co-reflection levels. The results showed that most learners in an online learning community reached an upper-middle co-reflection level while playing an inactive role in the co-reflection process. Moreover, higher-level learners were superior in dialog with various roles and were more involved in self-rethinking during the co-reflection process. In particular, they habitually began communication with peers and then with the teacher. Based on these findings, some implications for facilitating online co-reflection from the perspective of roles is also discussed.
1 March 2025 in International Journal of Multimedia Information Retrieval
The proliferation of Massive Open Online Courses (MOOCs) has created an urgent need for advanced course recommendation systems (RS). Course recommendations in MOOCs require transparent motivations to justify course selection, as there are often many courses with the same title, but which vary widely in content, duration, learning resources provided, and the academic authority of the instructor. Explainable recommendations are crucial to ensure that recommended courses fit well with learners’ needs and increase the chance of successful course completion, but unfortunately existing RS for MOOCs struggle to provide explainable recommendations. In this article, we present KnowPath , a novel RS for MOOCs, which generates effective and explainable recommendations. KnowPath uses open source Large Language Models (LLMs) to construct knowledge graphs (KGs) capable of accurately capturing complex relationships between MOOC entities (e.g., learners, instructors, educational resources) and employs Reinforcement Learning to align the output of an LLM with learner preferences. Extensive experiments on two public datasets (XueTang and COCO) demonstrate the superior performance and generalizability of KnowPath , underlining its potential to revolutionize the field of personalized online education.
Research on online collaborative learning has explored various methods of collaborative improvement. Recently, learning analytics have been increasingly adopted for ascertaining learners’ states and promoting collaborative performance. However, little effort has been made to investigate the transformation of collaborative states or to consider cognitive load as an essential factor for collaborative intervention. By bridging collaborative cognitive load theory and system dynamics modeling methods, this paper revealed the transformation of online learners’ collaborative states through data analysis, and then proposed an optimized mechanism to ameliorate online collaboration. A quasi-experiment was conducted with 91 college students to examine the potential of the optimized mechanism in collaborative state transformation, awareness of collaboration, learning achievement, and cognitive load. The promising results demonstrated that students learning with the optimized mechanism performed significantly differently in collaboration and knowledge acquisition, and no additional burden in cognitive load was noted.