Applying genetic algorithms for student grouping in collaborative learning: A synthetic literature review

Abstract

Computer-Supported Collaborative Learning (CSCL) is one of the most promising innovations to enhance learning through peer interactions supported by technological advances. Collaborative learning refers to the teaching strategies whereby students are encouraged or required to work together in groups on certain learning activities. Thus, group formation is an important step to design effective CSCL environments. Adequate groups foster better interactions between members and boost learning outcomes. Nevertheless, group formation is a complex task and requires computational support to succeed. In this context, there are several studies focusing on the development of algorithms for composing student groups and evaluating them. One of the most effective approaches is the Genetic Algorithms, as it can handle numerous variables and generate optimal solutions according to the problem requirements. However, this research field is very confined. To the best of our knowledge, there is not any study that gathers and analyzes the research findings on the adoption of grouping genetic algorithm in CSCL. To fill this gap, fifteen researches on this field were selected and analyzed in order their contributions to be emerged. Thus, the scope of this paper is to give an overview on how genetic algorithms for student group formation are being applied in web-based collaborative learning environments and what facts need to be considered to develop efficient approaches.