Integration of Adaptive Collaborative Learning Process in a Hybrid Learning Environment

Abstract

Technology integration has been crucial in the practice of the learning process. The use of technology aims to find effective solutions to traditional learning problems. Despite the enormous efforts adopted, using e-learning systems was optional in many education systems. However, the COVID-19 health crisis has shown the importance of the transition to e-learning to ensure pedagogical continuity. According to several studies that have measured the impact of COVID-19 on education systems and the adopted solutions, blended learning represents an effective solution for combining the advantages of face-to-face and distance learning. But the implementation strategies regarding this mode of learning are still limited. For this purpose, we propose a hybrid learning model based on collaborative work through an intelligent assignment of learner roles. This approach aims to support adaptive learning via a hybrid learning environment. The proposed solution is based mainly on collaborative work as an active learning method, using the Naïve Bayes algorithm and Belbin theory. The usefulness of collaborative work is to keep the learning rhythm between face-to-face and distance learning and to encourage learners' engagement and motivation through this mode of learning. According to Belbin's theory, the results of this work propose an adequate role for each learner. This intelligent assignment leads the learner to live the learning situation and not undergo it.