Collaborative Learning Team Formation: A Cognitive Modeling Perspective

With a number of students, the purpose of collaborative learning is to assign these students to the right teams so that the promotion of skills of each team member can be facilitated. Although some team formation solutions have been proposed, the problem of extracting more effective features to describe the skill proficiency of students for better collaborative learning is still open. To that end, we provide a focused study on exploiting cognitive diagnosis to model students’ skill proficiency for team formation. Specifically, we design a two-stage framework. First, we propose a cognitive diagnosis model SDINA, which can automatically quantify students’ skill proficiency in continuous values. Then, given two different objectives, we propose corresponding algorithms to form collaborative learning teams based on the cognitive modeling results of SDINA. Finally, extensive experiments demonstrate that SDINA could model the students’ skill proficiency more precisely and the proposed algorithms can help generate collaborative learning teams more effectively.