Composing High-Heterogeneous and High-Interaction Groups in Collaborative Learning with Particle Swarm Optimization

Computer supported collaborative learning (CSCL) which helps to increase the social interactions among learners without the constraint of time and space as it would be in real classrooms has prevailed among e-learning technologies. However,the studies of group formation that involve with diverse characteristics such as learning style of students or concern with interactions among students have rarely been conducted. Due to the fact that allocating students into groups is an NP-hard problem, we propose a particle swarm optimization (PSO) algorithm to cope with the problem of constructing high-heterogeneous and high interaction groups for students in classrooms to enhance the effect of CSCL. A real case with 61 students in a classroom was illustrated for our PSO grouping algorithm. The results indicate that students could be allocated into groups with higher degrees of heterogeneity among groups and interactions among members in a rational execution time.