Towards an Approach for Recommending Learning Steps in an Online Course Based on the Ant Colony Algorithm
Souheyl Mallat, Ala Eddine Mouissaoui · Procedia Computer Science · 2025
This paper proposes a method for recommending learning paths within the context of an Online Course Framework (OCF). This method leverages Ant Colony Optimization (ACO), a swarm intelligence technique, to differentiate learning paths based on the activities explored by learners, thereby enhancing their learning experience. To identify optimal paths and assess their impact, the approach combines the instructor’s initial recommendations with an analysis of learner progress and stored performance data, drawing inspiration from the work of Aziz Dahbi. The identification process integrates statistical and probabilistic reasoning and includes a preparatory phase at the start of the course to better guide learners. The method was validated through experimental case studies, which revealed the emergence of a specific learning path that led to a significant improvement in learner success rates. This innovative approach demonstrates strong potential to increase the effectiveness and personalization of online learning.