An Improved Genetic Algorithm Approach for Optimal Learner Group Formation in Collaborative Learning Contexts

Abstract

Collaborative learning has been widely used in educational contexts. Considering that group formation is one of the key processes in collaborative learning, the aim of this paper is to propose a method to obtain inter-homogeneous and intra-heterogeneous groups. In this method, the group formation problem is translated into a combinatorial optimization problem, and an improved genetic algorithm approach is also proposed to cope with this problem. To evaluate the proposed method, we carry out computational experiments based on eight datasets with different levels of complexity. The results show that the proposed approach is effective and stable for composing inter-homogeneous and intra-heterogeneous groups.