Novel Machine Learning Approach for an Adaptive Learning System Based on Learner Performance

This study addresses the need for a clearer definition of the contribution of AI-based adaptive learning approaches in the educational context. Specifically, we focus on the critical role of the learner model, which encompasses a wide range of factors such as the learner's unique qualities, knowledge, abilities, behaviors, preferences, and distinctions. These factors are paramount in tailoring the learning experience, including the choice of learning materials, pedagogical strategies, and presentation styles. In response to this challenge, we introduce a novel approach that leverages self-esteem (SE), emotional intelligence (EQ), and demographic data to predict and anticipate student performance. Through the implementation of this approach, we can recognize students who could be at danger and make necessary adjustments to all aspects of the learning process, including adapting pedagogies, teaching methods, and the delivery of learning materials. This contribution aims to enhance the effectiveness of AI-driven adaptive learning systems in meeting the diverse needs of individual learners.