Topic Detection for Online Course Feedback using LDA

Sayan Unankard, Wanvimol Nadee

In an online course, student feedback is used widely in order to enhance the quality of teaching and learning process by improving the teacher-student relationship. If a lecturer wants to get a summary of these comments, the lecturer has to manually read and summarize all these comments. However, dealing with a very large number of comments is difficult. In this paper, we proposed an approach for topic detection for online course feedback by adopting Latent Dirichlet Allocation (LDA). The course feedback from the website of Coursera (i.e., Machine Learning course) is used to demonstrate the effectiveness of our approach.