A genetic-algorithm approach for balancing learning styles and academic attributes in heterogeneous grouping of students

Abstract

Cooperative learning is an instructional approach in which students work together in small groups in order to achieve a common academic goal. In the context of cooperative learning, students in classrooms tend to learn more by sharing their experiences and knowledge. In addition, a diversity of educational backgrounds and student learning styles can be used to build heterogeneous groups of students. In this paper, we propose an approach for the group composition, regarding the index of learning styles (ILS) questionnaire and prior educational knowledge in order to achieve the mechanism for equity among groups and ensure that heterogeneous students are distributed optimally within the group formation. This causes the search for an optimized group composition of all students to become a more complex and becomes a timeconsuming task. Therefore, the proposed algorithm mimics the natural process of a genetic algorithm in order to achieve optimal solutions. In addition, we have implemented our algorithm to construct student groups. A case study shows that the algorithm enhances the quality of the group formation of heterogeneous students leading to better solutions.