A Hybrid Recommender System for MOOC Integrating Collaborative and Content-based Filtering
Samina Amin, Muhammad Ali Zeb · 2024
Massive open online courses (MOOCs) have been incredibly popular in recent years, providing top-level education to a global population. However, because of the abundance of content offered on MOOC platforms, it can be difficult for students to choose the courses that best suit their interests and academic objectives. Moreover, in academia, each learner has a unique set of skills, knowledge, understanding, adaptive difficulty levels, and learning capacities that they bring to the learning experience. This chapter will examine the development and use of an intelligent MOOC recommender system (RS) to address these problems. RSs have emerged as a valuable tool to assist learners in discovering relevant courses based on their preferences and past behavior. In this chapter, we explore how RS works in the context of MOOC, going beyond prediction accuracy. To this end, the chapter explores a hybrid approach combined with content-based (CB) and collaborative filtering (CF) to recommend the best courses to the learner. Furthermore, the chapter also explores evaluation indexes with examples that are popularly used in RS. The suggested approach relies on e-learning filtering to determine how the student should study best and to suggest learning content that complements their profile and e-learning experiences.