Socially Shared Regulation (SSRL) contributes to collaborative learning success. Recent advancements in Artificial Intelligence (AI) and Learning Analytics (LA) have enabled examination of this phenomenon’s temporal and cyclical complexities. However, most of these studies focus on students’ verbalised interactions, not accounting for the intertwined ’silent pauses’ that can index learners’ internal cognitive and emotional processes, potentially offering insight into regulation’s core mental processes. To address this gap, we employed AI-driven LA to explore the deliberation tactics among ten triads of secondary students during a face-to-face collaborative task (2,898 events). Discourse was coded for deliberative interactions for SSRL. With the micro-annotation of ‘silent pause’ added, sequences were analysed with the Optimal Matching algorithm, Ward’s Clustering and Lag Sequential Analysis. Three distinct deliberation tactics with different patterns and characteristics involving silent pauses emerged: i) Elaborated deliberation, ii) Coordinated deliberation, and iii) Solitary deliberation. Our findings highlight the role of ‘silent pauses’ in revealing not only the pattern but also the dynamics and characteristics of each deliberative interaction. This study illustrates the potential of AI-driven LA to tap into granular data points that enrich discourse analysis, presenting theoretical, methodological, and practical contributions and implications.

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.

In recent years, we have gradually adopted the applications of artificial intelligence in education (AIED) to improve our understanding of students’ learning and enhance their learning experiences. AIED can have a profound impact on the educational landscape, influencing the role of all involved in education. The adoption of AIED and its related large-scale data collection and analysis to do with learners seriously concern human-rights and related ethical and privacy aspects. This paper presents conceptual research establishing a data ethics framework for AIED by mapping and analyzing international organizations’ current policies and guidelines. In addition to contributing to the discussion of the benefits of AI in education, this paper raises data ethics concern for AIED. The proposed framework helps promote the design, development, and implementation of ethical and trustworthy AIED.