Approach for Eliciting Learners' Preferences in Moocs Through Collaborative Filtering

Abstract

MOOCs (massive open online courses) quickly become essential components for assuring educational continuity and supporting future life and ways of working. Therefore, there is a need for MOOCs to move away from its old model. This framework will present an algorithm-based recommendation system that will employ collaborative filtering based on MOOC learners' preferences. Collaborative filtering is a technique for anticipating a user's interests by studying the users' preferences who are similar to the individual in question. This approach ensures the analysis of many elements using the participants' rating choices. A recommendation system is becoming increasingly common in online study activities; we want to study how it might help learning and promote a more effective involvement. This study will provide an insight into the existing literature on recommendation systems for online learning and their contribution to supporting learners. We will base our proposed recommendation system on the evaluation of course content. The idea is that learners rate the courses and content they have registered for on the platform between 1 and 5. Following the rating, we extract the data into a comma-separated values (CSV) file and use Python programming to provide recommendations using data from learners with similar rating patterns. The purpose was to utilize Python programming to propose courses to different users in a text editor mode. We will use similar rating patterns via collaborative filtering to recommend courses to various learners, enhancing their learning experience and passion.