Review and classification of content recommenders in E-learning environment

E-learning recommender systems are becoming more popular due to the massive learning materials available online and the changing pedagogy. A content recommender system in the e-learning domain helps the learners by suggesting appropriate learning resources based on their preferences and learning goals. This paper presents a literature review on the recent studies conducted on content recommenders in the e-learning domain. The articles chosen for the review are mainly studies on personalized and adaptive learning systems. For that, we have collected and analyzed a set of journal papers published in this field during the period 2015–2020. Based on the analysis, we have categorized the different recommendation techniques, data inputs, algorithms, similarity measures, and evaluation metrics used in these studies. The paper also highlights the current trends in the recommendation process and the merits and demerits of the selected studies. Thus it provides an insight into the current state-of-the-art.