Sentiment Analysis Based on Online Course Feedback Using Textblob and Machine Learning Techniques

Online education has grown significantly in popularity over the last several years, providing students with a flexible and convenient way to study. Despite its many benefits, this flexible approach of learning requires ongoing assessment and feedback to ensure that it is being improved and improved. In order to develop a model that can accurately classify learner attitudes as positive, negative, or neutral, this study explores the field of sentiment analysis in the context of online course feedback. In this study, we analyzed the students' sentiments regarding their courses based on their feedback on online courses and tried to predict their sentiments. We have used the Coursera Course Reviews Dataset, which contains 107018 data records of used reviews and comments. Six machine learning techniques (Support Vector Machines (SVM), Naive Bayes, Logistic Regression, Decision Trees, Random Forests, and the AdaBoost) were applied with four performance measurement metrics. One of our models, Logistic Regression, outperformed the other models with an accuracy of 97.31%. Our findings demonstrate that our model achieved the highest possible accuracy compared to previous relevant studies in this particular domain.