Exploring Temporal Dynamics of Interaction Density in Collaborative Problem Solving: A Study of Interactions Across Varying Time Granularities

Collaborative Problem Solving (CPS) has gained increasing attention for its role in fostering learners’ cognitive and social development in STEM education. However, little is known about how learners interact dynamically within a group at different time granularities, and how these dynamics in interaction are associated with collaborative processes and performance. This gap largely stems from a lack of exploration of the temporal dimension of interactions, leading to a lack of nuanced insights into moment-to-moment dynamics in CPS. This study highlights the potential of modeling group interaction density of temporal dimension in online CPS activities and investigates the impact of temporal group interaction density on the CPS process and outcomes. Specifically, the study utilized the cumulative weighted density to capture the holistic state of group interactions. Further, the study analyzes the difference in group interaction density across high- and low- performing groups by modeling the transition of interaction sequences through the Apriori association rule algorithm. Results indicate that temporal group interaction density cannot directly predict collaborative performance, but notable differences in collaborative processes were observed between high-and low-performing groups with varying interaction densities. These findings inform the design of targeted interventions and support process mining of CPS interactions, offering practical implications for the assessment and development of CPS skills.