Online Collaborative Learning Grouping Method Based on Immune Genetic Algorithm

Abstract

Online learning platforms such as MOOCs have been widely applied, on which students can learn online courses anytime and anywhere, and can also be divided into groups to conduct a learning task. Through team collaboration, students' comprehensive abilities can be improved, including learning, organization, communication, teamwork ability, etc. Reasonable grouping is the basis and focus of efficient collaborative learning. The existing intelligent optimization algorithms used to solve the combinatorial optimization problem of student grouping still have the limitation of being easy to fall into the local optimum and blind search. In response to this problem, we study an efficient student grouping algorithm for online collaborative learning in this paper. Firstly, we integrate an immune strategy into the Genetic Algorithm to form a new algorithm called Immune Genetic Algorithm (IGA). Secondly, we design a fitness function according to the grouping goal of “Heterogeneity within a group, homogeneity between groups”. Finally, we evaluate the performances of the algorithms through experiments based on a real data set. The grouping results show that compared with the Genetic Algorithm, the proposed Immune Genetic Algorithm improves the search efficiency and stability, and can get grouping results with better fitness value.