Opinion Mining Models for Learner Feedback on Massive Open Online Courses

Feedback and ratings in MOOCs are important for course design and learner satisfaction. This work studies sentiment analysis methods for learner feedback to better understand user experience and identify patterns in positive and negative responses. The research evaluates multiple machine learning methods, including Logistic Regression, KNN, Naive Bayes, Decision Tree, and Random Forest, using MOOC feedback as a case study. The goal is to understand learner sentiment and support course improvement through data-driven insights.

In 2022 International Conference on Electronic Systems and Intelligent Computing (ICESIC)