Paper Contents
Abstract
In the rapidly evolving landscape of online education, assessing student participation is crucial for enhancing engagement and learning outcomes. This study presents a novel approach to automatically evaluate studentsparticipation using a bagging ensemble deep learning method. By leveraging a diverse set of deep learning models, our framework improves the accuracy and robustness of participation assessment compared to traditional metrics. We collected data from various online courses, including interaction logs, assignment submissions, and forum contributions. The proposed method combines the strengths of multiple classifiers, effectively capturing the nuanced patterns of student engagement. Our experiments demonstrate that the ensemble model significantly outperforms individual models in predicting participation levels, highlighting its potential as a reliable tool for educators. This research contributes to the growing body of work on data-driven educational assessment and offers a scalable solution to monitor and enhance student involvement in online learning environments.
Copyright
Copyright © 2024 D.Vikranthnivas. This is an open access article distributed under the Creative Commons Attribution License.
