Dynamic Re-Composition of Learning Groups Using PSO-Based Algorithms.

摘要: In collaborative learning contexts, the problem of automatically forming effective groups gets considerably complex with larger class sizes, e.g. in MOOCs. Additionally, group dynamics caused by high dropout rates currently observable on online open course platforms poses challenges to formation strategies. To address these problems, this paper presents PSO-based algorithms dynamically re-compose groups. addition static grouping criteria (such as MBTI personality types), take into account factors success rate and satisfaction during re-composition. We carried out simulations based randomly generated sample data. The experimental results show that proposed approach performs better than traditional exhaustive or random methods.