Developing an Adaptive Learning Recommendation Algorithm and System for MOOCs

Abstract

Massive Open Online Courses (MOOC) based learning platform had totally changed the educational environment by providing easy and accessible learning opportunities for global learners. But even such environment display high dropout and low learner engagement which remain a significant challenge to be addressed. To handle the challenge of this study, propose an Adaptive Learning Recommendation System (ALRS) that is designed to personalize learning paths based on individual preferences and performance metrics. The study employed Open University Learning Analytics Dataset (OULAD) and build recommendation model that combine k-means Clustering, Content-based Filtering, Collaborative Filtering, and Random Forest (RF) classifiers to make course recommendations. The proposed model have shown better recommendation when compared to other models with Precision of 0.92, Recall of 0.89, F1 Score of 0.90, and AUC of 0.95. Also the proposed model had shown the lowest Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) at 0.042 and 0.205, respectively.