Work

Optimising team dynamics: The role of AI in enhancing challenge-based learning participation experience and outcomes

Year: 2025

Type: article

Abstract: The approach of engaging students with real-world challenges to enhance collaboration and problem-solving has attracted significant interest from scholars and practitioners across diverse disciplines. Often called Challenge-Based Learning (CBL), this educational approach emphasises developing collaborative and problem-solving skills, with significant learning occurring within team settings. Prior studies highlight the influence of team composition on the efficacy of learning outcomes, pointing out that factors such as gender diversity, personality trait diversity, and a wide range of skills affect team dynamics and performance. Despite these insights, the practical organisation of these teams remains a challenge, often reliant on ad-hoc methods driven primarily by the nature of the setting at hand. Importantly, CBL is typically assessed through the final product, neglecting the impact of CBL on how the participants experience the overall process. That is, CBL is usually considered effective if the outcome is of high quality, ignoring participants' experience and participation quality. This study investigates the potential of an Artificial Intelligence team composition algorithm to improve participation quality and outcomes in collaborative CBL environments. • Enhance challenge-based learning participation experience. • Operationalising the concept of relational well-being as a measure for participation quality. • Empirically quantify the benefits of using AI during team composition concerning participation quality. • Explore different algorithm configurations to provide guidelines on configuring the AI algorithm to trade-off between participants' experience vs. teams' outcomes.

Source: Computers and Education Artificial Intelligence

DOI: 10.1016/j.caeai.2025.100388