Machine Learning Approaches for Analysing Sentiment in Reviews on Massive Open Online Courses

With the advancement of online learning, it is observed that there is an exponential growth of data and information across the internet which leads the students to enroll for Massive Open Online Courses (MOOC) [25]. Regardless, users struggle with choosing the right course given its credibility and complementary aspects. Many MOOC sites provide a review option for users’ feedback. Students generally opt for any course based on user ratings and feedback comments available on MOOC. Therefore, analyzing online reviews gives more exhaustive feedback of a course rather than assessing quantified ratings given by users. To predict the sentiment represented in a piece of text, we employed different machine learning models like convolutional neural networks (CNN), recurrent neural network (RNN), long short term memory (LSTM), etc. to perform comparative sentiment analysis by drawing an analogy between reviews and ratings data This paper provides insights for the user engagement and satisfaction and offers insightful analysis of MOOC learner’s experience and recommendations for pertinent course selection.