An Adaptive Learning Approach for Better Retention of Learners in MOOCs

Nowadays, the MOOC (Massive Open Online Course) revolution is gaining growing popularity due to the large number of open online courses. However, the retention rate of learners, which is generally around 10%, raises the question of the effectiveness of this mode of education. Our main objective in this paper is to design a new model to improve the courses completion rate and fight against the dropping out through an adaptive e-learning system for each learner, so that the proposed course correspond to the adequate way the learners could accomplish their learning process. The model will be realized by exploiting the traces left during the users' interactions with their learning environment. By using these traces, we get all pertinent information related to the learner profile. Furthermore, we will generate via ant colony algorithms, recommendations tailored to each learner.