Enhancing Differentiated Learning in Virtual Courses Through AI-Driven Recommender Systems

Virtual education has emerged as a paradigm in contemporary training, particularly after the COVID-19 pandemic highlighted its viability as an alternative to traditional in-person education. However, most current virtual courses and their contents are designed statically, assuming all students learn the same way. In this paper, we propose enhancing differentiated learning in virtual environments by integrating Artificial Intelligence (AI) at various stages of a virtual course.Our proposal for enhancing differentiated learning in virtual environments through AI involves three stages. First, we use the Felder-Silverman Learning Styles Model to identify students’ learning styles. In the second stage, we develop a recommender system to deliver personalized resources tailored to each student’s learning style. Finally, we compare different machine learning techniques in the early prediction of student performance, with the goal of identifying features of student behaviour that could inform the development of our recommender system.In this way, this paper provides a comprehensive overview of a didactic strategy to enhance differentiated learning in virtual environments integrating AI techniques. The application of AI across various stages of course design and the learning process aims to optimize student engagement, satisfaction, and academic performance in virtual settings.