PERSONALIZED LEARNER RECOMMENDATIONS

Abstract

In the evolving landscape of education, effective collaboration among students is crucial for maximizing learning outcomes. Traditional methods of group formation often fail to account for the diverse skills, interests, and learning styles of students, leading to suboptimal group dynamics and performance. This study explores the application of a personalized learner recommendation system designed to enhance group dynamics in collaborative learning environments. By leveraging data-driven techniques, the system analyzes student profiles to form balanced and cohesive groups. A controlled experimental design was conducted with 60 master’s students at Ecole Normale Supérieure (ENS) of Abdelmalek Essaadi University in Morocco, divided into a control group and an experimental group. The experimental group utilized the recommendation system for group formation, while the control group was formed randomly without the system. The study measured three key dependent variables: total time invested in the collaborative project, the percentage of project tasks completed, and the frequency of interactions among group members. The results of the study indicate that the experimental group, which used the personalized recommendation system, outperformed the control group in all three measured variables. The experimental group invested more time in the project, completed a higher percentage of tasks, and demonstrated a greater frequency of interactions. These findings suggest that the recommendation system effectively increased student engagement, improved group productivity, and fostered better communication among group members. This research highlights the potential of personalized recommendation systems to transform collaborative learning by optimizing group formation. The study’s findings offer valuable insights for educators and instructional designers seeking to enhance the effectiveness of collaborative learning in digital and traditional educational settings. Future research should explore the application of such systems in diverse educational contexts and consider integrating qualitative assessments to capture student experiences and perceptions. Overall, the integration of personalized recommendation systems into educational practices represents a significant step toward achieving more personalized, inclusive, and effective learning experiences.