A VARK Learning Style-Based Recommendation System for Adaptive E-Learning – Pilot Study

This research investigates an adaptive e-learning system designed to offer personalized learning experiences based on each learner’s needs, including learning style, and knowledge gaps. The system utilizes the VARK model and a recommendation engine with fuzzy logic approaches based on rules to customize materials. The system involved administering a VARK assessment to identify each learner’s learning style, monitored by pre/posttests to detect knowledge gaps. Findings from a pilot study revealed that this system significantly improved learner enhancement, engagement, satisfaction and motivation, in contrast with the standard e-learning system. These outcomes emphasize the importance of recognizing individual learning styles and addressing targeted knowledge shortages. By delivering tailored learning paths that suit each student’s unique learning, the proposed system overcomes certain limitations in existing studies, offering a scalable option for better educational results. This approach shows potential for improving e-learning by reducing gaps in personalization and efficiency and finding learning preferences for students.