Students Group Formation Based on Case-Based Reasoning to Support Collaborative Learning

The group formation has been widely investigated since it is a crucial aspect to perform collaborative work. However, there is no consensus about the best set of metrics or how to combine student's characteristics to improve group interactions, so it has been considered a challenge. Aiming to cope with that, this work proposes the use of case-based reasoning to suggest groups for collaboration based on the metrics and previous groups' performances stored in a case base. We gathered data from students working on collaborative tasks to build a case base and ran a grouping experiment in a class of undergraduates to verify the effectiveness of the proposal. The results evidenced that grouping based on the Big Five improved students' interactions.

---

1. Track 1: Artificial Intelligence

---

2. Technical Session: 15th International Symposium Advances in Artificial Intelligence and Applications

---

3. Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).