Towards Effective Collaborative Learning: A Machine Learning Solution for Identifying and Assisting Inactive Students

Abstract

Learning plays an important role in everyone’s life. In schools there are various methods used to teach students new skills, and how well students perform is crucial. And in the learning process, one effective method is collaborative learning, where students work together in groups to achieve common goals. In schools it may possible that there may be multiple groups performing collaborative learning activity and, in few groups, in some cases it is observed that the few students never talk in group and for such a kind of student continuous monitoring is required and it seems to be a difficult task for the teacher to predict whether the concept is understood to the student or not. This research aims to address this issue by designing a machine learning-based model. The model helps to monitor individual students in collaborative learning groups, which will help to focus on inactive students. Proposed system would help teachers to work on individual students' performance in each group. Ultimately, this work contributes to making collaborative learning more effective and inclusive by ensuring that every student's progress has monitored and supported for learning performances of individual student of group activities.