Social Media Sentiment Analysis Based on Domain Ontology and Semantic Mining

  • Daoping WangEmail author
  • Liangyue Xu
  • Amjad Younas
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10934)


The rapid development of social media has made more and more users express their opinions, feelings, and attitudes toward various things through different forums like Twitter, WeChat, and Weibo. However, most existing works just focus on specific product categories to construct the domain ontology, which is a quite narrow use of domain ontology. We propose a new construction of domain ontology based on the semantic features of social media. The topic of posts and opinions, also known as topic-opinion pairs, are identified with the domain ontology. The sentiment polarities are determined with the help of the given sentiment polarities. The sentiment polarity of an unknown post is calculated by the weighted average of the sentiment polarities of topics and opinions contained in the post. Preliminary results show that the application of domain ontology can effectively identify the topic-opinion pairs, and according to the known polarity of posts can effectively classify the topic-opinion pairs. The accuracy of sentiment classification is increasing.


Domain ontology Semantic mining Associating mining Social media 


  1. 1.
    Marstawi, A., Sharef, N.M., Aris, T.N.M.: Ontology-based aspect extraction for an improved sentiment analysis in summarization of product reviews. In: International Conference on Computer Modeling and Simulation, pp. 100–104. ACM, Canberra (2017)Google Scholar
  2. 2.
    Jung, H., Park, H.A., Song, T.M.: Ontology-based approach to social data sentiment analysis: detection of adolescent depression signals. J. Med. Internet Res. 19(7), 259 (2017)CrossRefGoogle Scholar
  3. 3.
    Sreejith, D., Devika, M.P., Tadikamalla, N.S., Mathew, S.V.: Sentiment analysis of English literature using rasa-oriented semantic ontology. Ind. J. Sci. Technol. 10(24), 1–11 (2017)CrossRefGoogle Scholar
  4. 4.
    Hu, M., Liu, B.: Mining opinion features in customer reviews. In: National Conference on Artificial Intelligence, pp. 755–760. AAAI Press, San Jose (2004)Google Scholar
  5. 5.
    Wilson, T., Hoffmann, P., Somasundaran, S.: OpinionFinder: a system for subjectivity analysis. In: Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP, Canada, pp. 347–354 (2005)Google Scholar
  6. 6.
    Kim, S.M., Hovy, E.: Extracting opinions, opinion holders, and topics expressed in online news media text. In: Proceedings of the Workshop on Sentiment and Subjectivity in Text, pp. 1–8. ACL, Sydney (2006)Google Scholar
  7. 7.
    Kobayashi, N., Inui, K., Matsumoto, Y., Tateishi, K., Fukushima, T.: Collecting evaluative expressions for opinion extraction. In: Su, K.-Y., Tsujii, J., Lee, J.-H., Kwong, O.Y. (eds.) IJCNLP 2004. LNCS, vol. 3248, pp. 596–605. Springer, Heidelberg (2005). Scholar
  8. 8.
    Zhuang, L., Jing, F., Zhu, X.Y.: Movie review mining and summarization. In: Proceedings of the 15th ACM International Conference on Information and Knowledge Management, pp. 43–50. ACM, New York (2006)Google Scholar
  9. 9.
    Jakob, N., Gurevych, I.: Extracting opinion targets in a single and cross-domain setting with conditional random fields. In: Conference on Empirical Methods in Natural Language Processing, Cambridge (2010)Google Scholar
  10. 10.
    Tan, C., Lee, L., Tang, J.: User-level sentiment analysis incorporating social networks, pp. 1397–1405. ACM, San Diego (2011)Google Scholar
  11. 11.
    Go, A., Bhayani, R., Huang, L.: Twitter sentiment classification using distant supervision. Cs224n Project Report, pp. 1–12 (2009)Google Scholar
  12. 12.
    Alexander, P., Patrick, P.: Twitter as a corpus for sentiment analysis and opinion mining. In: Proceedings of International Conference on Language Resource and Evaluation, Lisbon, pp. 1320–1326 (2010)Google Scholar
  13. 13.
    Barbosa, L., Junlan, F.: Robust sentiment detection on Twitter from biased and noisy data. In: Proceedings of the 23rd International Conference on Computational Linguistics, Beijing, pp. 36–44 (2010)Google Scholar
  14. 14.
    Davidiv, D., Tsur, O., Rappoport, A.: Enhanced sentiment learning using Twitter hashtags and smileys. In: Proceedings of the 23rd International Conference on Computational Linguistics, Beijing, pp. 241–249 (2010)Google Scholar
  15. 15.
    Jain, J.P., Awati, J., Alzende, H.: Opinion analysis of text on the basis of three domain classification. In: International Conference on Automatic Control and Dynamic Optimization Techniques. IEEE, Pune (2017)Google Scholar
  16. 16.
    Ding, S.C., Ma, M.R., Li, X.: Study of subjective sentence identification oriented to Chinese micro blog. J. China Soc. Sci. Tech. Inf. 33(2), 175–182 (2014). (in Chinese)Google Scholar
  17. 17.
    Ramesh, S., Duerson, D., Ephraims, T.: A Managerial Perspective on Analytics. Chinese Machine Press, Beijing (2015)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.University of Science and Technology BeijingBeijingChina

Personalised recommendations