Sentiment Analysis for University Students’ Feedback

  • Nguyen Thi Phuong GiangEmail author
  • Tran Thanh Dien
  • Tran Thi Minh Khoa
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1130)


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 Naïve Bayes, Maximum Entropy and Support Vector Machine on our annotated data. The result proves that Maximum Entropy algorithm is better than Naïve 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.


Sentiment analysis Opinion mining Student feedback 


  1. 1.
    Kieu, B.T., Pham, S.B.: Sentiment analysis for vietnamese. In: 2010 Second International Conference on Knowledge and Systems Engineering (KSE), pp. 152–157 (2010)Google Scholar
  2. 2.
    Altrabsheh, N., Gaber, M., Cocea, M.: SA-E: sentiment analysis for education. In: 5th KES International Conference on Intelligent Decision Technologies (2013)Google Scholar
  3. 3.
    Mac Kim, S., Calvo, R.A.: Sentiment analysis in student experiences of learning. In: Educational Data Mining 2010 (2010)Google Scholar
  4. 4.
    Achen, R.M., Lumpkin, A.: Evaluating classroom time through systematic analysis and student feedback. Int. J. Sch. Teach. Learn. 9, 4 (2015)Google Scholar
  5. 5.
    Phuc, D., Phung, N.T.K.: Using Naïve Bayes model and natural language processing for classifying messages on online forum. In: 2007 IEEE International Conference on Research, Innovation and Vision for the Future, pp. 247–252 (2007)Google Scholar
  6. 6.
    Smith, M.K., Jones, F.H., Gilbert, S.L., Wieman, C.E.: The classroom observation protocol for undergraduate STEM (COPUS): a new instrument to characterize university STEM classroom practices. CBE Life Sci. Educ. 12, 618–627 (2013)CrossRefGoogle Scholar
  7. 7.
    Delen, D.: A comparative analysis of machine learning techniques for student retention management. Decis. Support Syst. 49, 498–506 (2010)CrossRefGoogle Scholar
  8. 8.
    Duyen, N.T., Bach, N.X., Phuong, T.M.: An empirical study on sentiment analysis for Vietnamese. In: 2014 International Conference on Advanced Technologies for Communications (ATC 2014), pp. 309–314 (2014)Google Scholar
  9. 9.
    Liu, B.: Sentiment analysis and opinion mining. Synth. Lect. Hum. Lang. Technol. 5, 1–167 (2012)CrossRefGoogle Scholar
  10. 10.
    Rohrer, B.: How to choose algorithms for Microsoft Azure machine learning (2015)Google Scholar
  11. 11.
    Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing contextual polarity in phrase-level sentiment analysis. In: Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, pp. 347–354 (2005)Google Scholar
  12. 12.
    Klein, D., Manning, C.: Maxent models, conditional estimation, and optimization. In: HLTNAACL 2003 Tutorial (2003)Google Scholar
  13. 13.
    Joachims, T.: SVM-Light Support Vector Machine, vol. 19. University of Dortmund (1999).
  14. 14.
    Vryniotis, V.: Developing a Naive Bayes text classifier in JAVA, 27 January 2014 (2014)Google Scholar
  15. 15.
    Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2, 27 (2011)Google Scholar
  16. 16.
    Klein, D.: The Stanford Classifier. The Stanford Natural Language Processing Group (2003)Google Scholar
  17. 17.
    Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Ijcai, pp. 1137–1145 (1995)Google Scholar
  18. 18.
    Socher, R., Perelygin, A., Wu, J.Y., Chuang, J., Manning, C.D., Ng, A.Y., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), p. 1642 (2013)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Nguyen Thi Phuong Giang
    • 1
    Email author
  • Tran Thanh Dien
    • 2
  • Tran Thi Minh Khoa
    • 1
  1. 1.Industrial University of HCM City-IUHHCMCVietnam
  2. 2.Ngo Si Lien High SchoolHo Chi Minh CityVietnam

Personalised recommendations