An improved genetic approach for composing optimal collaborative learning groups

摘要

Collaborative learning is an effective strategy for promoting learning in both traditional face-to-face and online environments. When applying it, students should be assigned to best collaborative groups at the first step, which is called the learner group formation task. In previous studies, various approaches have been proposed to solve this problem. However, they failed to meet all the problem requirements. To address this problem, a generic group formation method that covers all aspects of the problem is proposed in this study. In this method, all requirements of the learner group formation problem are formulated into an integrated mathematical model and an improved genetic algorithm is proposed to solve the model and obtain optimal learning groups to meet various grouping requirements for different educational contexts. To analyse the performance of the proposed approach from a computational perspective, a series of computational experiments are conducted based on eight simulation datasets with different levels of complexity. The simulation results indicate that the proposed method is effective and stable for solving the learner group formation problem. An empirical study is also carried out to validate the proposed approach from a pedagogical view by comparing it with two traditional group formation strategies. The results show that groups formed through the proposed method produce better outcomes than others in terms of group grades, individual grades and student satisfaction.