부산대학교 도서관

Recent advances in Learning Analytics (LA) and Artificial Intelligence (AI) have enabled us to gain a better understanding of socially shared regulation (SSRL), which is in collaborative learning. Although recent progress in studying SSRL with LA and AI has provided holistic insights into the temporal and cyclical processes of SSRL, few studies have investigated SSRL processes at a granular level. To address these limitations, we utilise AI techniques to explore the sequences of group-level deliberation as a process and its pattern through cognitive and emotional regulation triggering events in the context of face-to-face collaborative learning. This study involved ten triads of secondary students ($\mathrm{N}=30$) working on a collaborative learning task and receiving regulation-triggering events during their learning. Results from Agglomerative Hierarchical Clustering (AHC) identified two distinct types of deliberation sequences with different approaches to regulation and collaboration practices: 1) the plan and implementation approach (PIA) focused on analysing, discussing, and collaborating; and 2) the trials and failures approach (TFA) focused on random idea testing. Interestingly, we found that most groups maintain the same approach in response to triggering events, emphasizing the importance of supporting learners to recognize and react to the emerging needs of regulation.