Sentiment Analysis for University Students' Feedback

Students' feedbacks have been an essential part of a range of higher educations as universities in Vietnam recently. This information could be about lectures, facilities, curriculum and how to improve them. The feedback is collected and processed manually at the end of each semester. We proposed to build a system which is ability to categorize students' feedbacks automatically. This system helps us save time, human resource and money for any higher education institutions. Firstly, we created university students' feedbacks data in two years and organized them into three classes: Positive, Negative and Neutral. We built the Vietnamese sentiment dataset with 5000 classified sentences. Then, we use three classifiers which are Naive Bayes, Maximum Entropy and Support Vector Machine on our annotated data. The result proves that Maximum Entropy algorithm is better than Naive Bayes and Support Vector Machine with the best score of 91.36%. With high accuracy, we confidently implement our results to develop the students' feedbacks system to detect students' opinions. With negative and positive students' opinions, we can adjust and improve the lectures, facilities, curriculum and make the quality of university better over the years.