Detecting Opinion Drift from Chinese Web Comments Based on Sentiment Distribution Computing

  • Daling Wang
  • Shi Feng
  • Dong Wang
  • Ge Yu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8180)


Opinion drift is regarded as the change of sentiment distribution in this paper. In opinion and sentiment mining, how to detect opinion drifts and analyze their reasons, is an important problem for Web public opinion analysis. To tackle this problem, an approach of opinion drift detection for Chinese Web comment is proposed. For a comment set during a long time about a hot event, the proposed approach first determines possible drift timestamps according to the change of comment number, computes different sentiment orientations and their distributions at these timestamps, detects opinion drift according to the distribution changes, and analyzes the influences of related events occurring in the timestamps. Extensive experiments were conducted in a real comment set of Chinese forum. The results show that drift timestamps determined and opinion drifts detected correspond to the real event, so the approach proposed in this paper is feasible and effective in the application of Web public opinion analysis.


Opinion Drift Detection Sentiment Distribution Opinion Mining 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bifet, A., Holmes, G., et al.: Detecting Sentiment Change in Twitter Streaming Data. Journal of Machine Learning Research - Proceedings Track (JMLR) 17, 5–11 (2011)Google Scholar
  2. 2.
    Cheng, L., Ke, Z., Shiue, B.: Detecting changes of opinion from customer reviews. In: FSKD 2011, pp. 1798–1802 (2011)Google Scholar
  3. 3.
    Choi, D., Kim, P.: Sentiment Analysis for Tracking Breaking Events: A Case Study on Twitter. In: Selamat, A., Nguyen, N.T., Haron, H. (eds.) ACIIDS 2013, Part II. LNCS, vol. 7803, pp. 285–294. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  4. 4.
    He, Y., Lin, C., et al.: Tracking Sentiment and Topic Dynamics from Social Media. In: ICWSM 2012 (2012)Google Scholar
  5. 5.
  6. 6.
  7. 7.
    Jiang, Y., Meng, W., Yu, C.: Topic Sentiment Change Analysis. In: Perner, P. (ed.) MLDM 2011. LNCS, vol. 6871, pp. 443–457. Springer, Heidelberg (2011)Google Scholar
  8. 8.
    Liu, B.: Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers (2012)Google Scholar
  9. 9.
  10. 10.
    Robertson, S.: Changes in Referents and Emotions over Time in Election-Related Social Networking Dialog. In: HICSS 2011, pp. 1–9 (2011)Google Scholar
  11. 11.
    Saito, K., Kimura, M., Ohara, K., Motoda, H.: Detecting Changes in Opinion Value Distribution for Voter Model. In: Salerno, J., Yang, S.J., Nau, D., Chai, S.-K. (eds.) SBP 2011. LNCS, vol. 6589, pp. 89–96. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  12. 12.
    Silva, I., Gomide, J., Veloso, A., et al.: Effective sentiment stream analysis with self-augmenting training and demand-driven projection. In: SIGIR 2011, pp. 475–484 (2011)Google Scholar
  13. 13.
    Widmer, G., Kubat, M.: Learning in the Presence of Concept Drift and Hidden Contexts. Machine Learning (ML) 23(1), 69–101 (1996)Google Scholar
  14. 14.
    Zhu, Y., Min, J., et al.: Semantic Orientation Computing Based on HowNet. Journal of Chinese Information Processing 20(1), 14–20 (2006) (in Chinese) Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Daling Wang
    • 1
    • 2
  • Shi Feng
    • 1
    • 2
  • Dong Wang
    • 1
  • Ge Yu
    • 1
    • 2
  1. 1.School of Information Science and EngineeringNortheastern UniversityP.R. China
  2. 2.Key Laboratory of Medical Image Computing, Ministry of EducationNortheastern UniversityP.R. China

Personalised recommendations