Massive Open Online Courses (MOOCs) have been widely disseminated due to the arrival of Web 2.0. In recent years, recommendation systems have been applied to support MOOCs users in choosing suitable learning materials (e.g., courses and videos) in this modality. However, implementing such systems remains a challenge since several recommendation aspects should be considered. In this work, we identify and analyze such aspects (e.g., inputs, approaches, and outputs), investigating several implementation possibilities based on the literature. Results show that collaborative filtering and content-based are the most used approaches. More than 60 techniques are used to support recommendations in MOOCs, and most of the studies focus on recommending courses. The main contributions are: (1) a better understanding of the aspects, benefits, and limitations of MOOCs recommendation; and (2) the identification of open issues and research trends, providing an analysis that can support the implementation of emerging recommendation systems for MOOCs.

Keywords

recommender system · massive open online course · e-learning · intelligent system · systematic mapping study