Deliberative Interactions for Socially Shared Regulation in Collaborative Learning: An AI-Driven Learning Analytics Study

Socially shared regulation in learning (SSRL) contributes to successful collaborative learning (CL). Empirical research into SSRL has received considerable attention recently, with increasingly available multimodal data, advanced learning analytics (LA), and artificial intelligence (AI) providing promising research avenues. Yet, integrating these with traditional datasets remains a challenge in SSRL research due to the misalignment between theoretical constructs, methodological assumptions, and data structure. To address this challenge and expand our understanding of the nature of SSRL, the present research adopted a human-AI collaboration approach in a threelayer analysis to examine group interactions in response to cognitive and emotional regulation triggering events. Two-level theoretical lenses - macro-level (regulatory aspects) and micro-level (deliberative interactions) - were used to analyze 2,125 utterances from video-recorded tasks of ten groups of three Finnish secondary students (N=30). Results showed two types of deliberation patterns for SSRL, namely 1) the Plan and Implementation Approach (PIA) associated with adaptive patterns, and 2) the Trials and Failure Approach (TFA) associated with maladaptive patterns. Our findings revealed that groups often fail to recognize, or are ill-equipped to respond to, emerging regulatory needs. These findings advance SSRL theories and research methodologies by utilizing AIenhanced LA to offer new insights into group dynamics and regulatory strategies.