Abstract:

Massive open online courses (MOOCs) are growing relatively rapidly in the education environment. There is a need for MOOCs to move away from its one-size-fit-all mode. This framework will introduce an algorithm based recommendation system, which will use a collaborative filtering method (CFM). Collaborative filtering method (CFM) is the process of evaluating several items through the rating choices of the participants. Recommendation system is widely becoming popular in online study activities; we want to investigate its support to learning and encouragement to more effective participation. This research will be reviewing existing literature on recommender systems for online learning and its support to learners’ experiences. Our proposed recommendation system will be based on course components rating. The idea was for learners to rate the course and components they have studied in the platform between the scales of 1 – 5. After the rating, we then extract the values into a comma separated values (CSV) file then implement recommendation using Python programming based on learners with similar rating patterns. The aim was to recommend courses to different users in a text editor mode using Python programming. Collaborative filtering will act upon similar rating patterns to recommend courses to different learners, so as to enhance their learning experience and enthusiasm.

Keywords:

Recommendation, collaborative, MOOC, Python, learners, massive open online courses.