Skip to main content
SpringerLink
Log in

Semi-supervised Stance-Topic Model for Stance Classification on Social Media

  • Conference paper
  • First Online:
Semantic Technology (JIST 2017)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 10675))

Included in the following conference series:

Abstract

Stance detection aims to automatically determine from text whether the author of the text is in favor of, against, or neutral towards a issue. Social media, such as Sina Weibo, reflects the general public’s stances towards different issues. Detecting and summarizing stances towards specific issues from social media is an important and challenging task. Although stance detection on social media has been studied before, previous work, most of which are based on supervised learning, may not work well because they suffer from its heavy dependence on training data. Other weakly supervised method also use some heuristic rules to select the posts with specific stances as training data, but these selected posts often concentrate on a few subtopics of the specific issue, these weakly supervised method can only train a biased stance classifier. To better detect stances toward specific issues, we consider to detect stances with a small number of labeled training data and a mass of unlabeled data. To integrate the supervised information into our model, we combine a discriminative maximum entropy (Max-Ent) component with the generative component. The Max-Ent component leverages hand-crafted features from labeled data to separate different stances. In this paper, we propose a semi-supervised topic model, Semi-Supervised Stance Topic Model (SSTM), that model stances and topics of the posts on social media. Since the posts on social media are short texts, we also incorporate the structural information of the posts, i.e., gender information, location information and time information, to aggregate posts for alleviating the context sparsity of the posts. The model has been evaluated on the selected posts on sina weibo, which talk about “the verbal battle of Han han and Fang zhouzi”, to classify the stance of each posts. Preliminary experiments have shown promising results achieved by SSTM. Moreover, we also analyze the common difficulties in stance detection on social media. Finally, we also visualize the subtopics of the given issue generated by SSTM.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    http://weibo.com/.

  2. 2.

    https://github.com/fxsjy/jieba.

References

  1. Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)

    MATH  Google Scholar 

  2. Bøhler, H., Asla, P., Marsi, E., Sætre, R.: IDI\(@\)NTNU at SemEval-2016 task 6: detecting stance in tweets using shallow features and glove vectors for word representation. In: Proceedings of SemEval@NAACL-HLT, pp. 445–450. ACL (2016)

    Google Scholar 

  3. Chieu, H.L., Ng, H.T.: Named entity recognition: a maximum entropy approach using global information. In: Proceedings of COLING (2002)

    Google Scholar 

  4. Diao, Q., Jiang, J., Zhu, F., Lim, E.-P.: Finding bursty topics from microblogs. In: Proceedings of ACL, pp. 536–544. ACL (2012)

    Google Scholar 

  5. Dias, M., Becker, K.: An heuristics-based, weakly-supervised approach for classification of stance in tweets. In Proceedings of WI, pp. 73–80. IEEE (2016)

    Google Scholar 

  6. Dong, Z., Dong, Q., Hao, C.: Hownet and its computation of meaning. In: Proceedings of COLING, pp. 53–56 (2010)

    Google Scholar 

  7. Ebrahimi, J., Dou, D., Lowd, D.: Weakly supervised tweet stance classification by relational bootstrapping. In: Proceedings of EMNLP, pp. 1012–1017. ACL (2016)

    Google Scholar 

  8. Geyer, C.J.: Practical Markov Chain Monte Carlo. Stat. Sci. 473–483 (1992)

    Google Scholar 

  9. Heinrich, G.: Parameter estimation for text analysis. Technical report (2005)

    Google Scholar 

  10. Igarashi, Y., Komatsu, H., Kobayashi, S., Okazaki, N., Inui, K.: Tohoku at SemEval-2016 task 6: feature-based model versus convolutional neural network for stance detection. In: Proceedings of SemEval@NAACL-HLT, pp. 401–407. ACL (2016)

    Google Scholar 

  11. Johnson, K., Goldwasser, D.: “All I know about politics is what I read in Twitter”: weakly supervised models for extracting politicians’ stances from Twitter. In: Proceedings of COLING, pp. 2966–2977 (2016)

    Google Scholar 

  12. Krejzl, P., Steinberger, J.: UWB at SemEval-2016 task 6: stance detection. In: Proceedings of SemEval@NAACL-HLT, pp. 408–412. ACL (2016)

    Google Scholar 

  13. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Proceedings of NIPS, pp. 1106–1114 (2012)

    Google Scholar 

  14. Lai, M., Farías, D.I.H., Patti, V., Rosso, P.: Friends and enemies of Clinton and Trump: using context for detecting stance in political tweets. CoRR, abs/1702.08021 (2017)

    Google Scholar 

  15. Li, C., Guo, X., Mei, Q.: Deep memory networks for attitude identification. In: Proceedings of WSDM, pp. 671–680. ACM (2017)

    Google Scholar 

  16. Lin, C., He, Y.: Joint sentiment/topic model for sentiment analysis. In: Proceedings of the 18th ACM Conference on Information and Knowledge Management. CIKM 2009, Hong Kong, 2–6 November 2009, pp. 375–384. ACM (2009)

    Google Scholar 

  17. Liu, C., Li, W., Demarest, B., Chen, Y., Couture, S., Dakota, D., Haduong, N., Kaufman, N., Lamont, A., Pancholi, M., Steimel, K., Kübler, S.: IUCL at SemEval-2016 task 6: an ensemble model for stance detection in Twitter. In: Proceedings of SemEval@NAACL-HLT, pp. 394–400. ACL (2016)

    Google Scholar 

  18. Ma, C., Wang, M., Chen, X.: Topic and sentiment unification maximum entropy model for online review analysis. In: Proceedings of WWW, pp. 649–654. ACM (2015)

    Google Scholar 

  19. Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. CoRR, abs/1301.3781 (2013)

    Google Scholar 

  20. Miller, D.J., Uyar, H.S.: A mixture of experts classifier with learning based on both labelled and unlabelled data. In: Proceedings of NIPS, pp. 571–577 (1996)

    Google Scholar 

  21. Misra, A., Ecker, B., Handleman, T., Hahn, N., Walker, M.A.: NLDS-UCSC at SemEval-2016 task 6: a semi-supervised approach to detecting stance in tweets. In: Proceedings of SemEval@NAACL-HLT, pp. 420–427. ACL (2016)

    Google Scholar 

  22. Mohammad, S., Kiritchenko, S., Sobhani, P., Zhu, X.-D., Cherry, C.: SemEval-2016 task 6: detecting stance in tweets. In: Proceedings of SemEval@NAACL-HLT, pp. 31–41. ACL (2016)

    Google Scholar 

  23. Patra, B.G., Das, D., Bandyopadhyay, S.: JU_NLP at SemEval-2016 task 6: detecting stance in tweets using support vector machines. In: Proceedings of SemEval@NAACL-HLT, pp. 440–444. ACL (2016)

    Google Scholar 

  24. Ramage, D., Manning, C.D., Dumais, S.T.: Partially labeled topic models for interpretable text mining. In: Proceedings of KDD, pp. 457–465. ACM (2011)

    Google Scholar 

  25. Tutek, M., Sekulic, I., Gombar, P., Paljak, I., Culinovic, F., Boltuzic, F., Karan, M., Alagic, D., Snajder, J.: Takelab at SemEval-2016 task 6: stance classification in tweets using a genetic algorithm based ensemble. In: Proceedings of SemEval@NAACL-HLT, pp. 464–468. ACL (2016)

    Google Scholar 

  26. Vijayaraghavan, P., Sysoev, I., Vosoughi, S., Roy, D.: Deepstance at SemEval-2016 task 6: detecting stance in tweets using character and word-level CNNs. In: Proceedings of SemEval@NAACL-HLT, pp. 413–419. ACL (2016)

    Google Scholar 

  27. Wallach, H.M., Mimno, D.M., McCallum, A.: Rethinking LDA: why priors matter. In: NIPS, pp. 1973–1981 (2009)

    Google Scholar 

  28. Wei, W., Zhang, X., Liu, X., Chen, W., Wang, T.: pkudblab at SemEval-2016 task 6: a specific convolutional neural network system for effective stance detection. In: Proceedings of SemEval@NAACL-HLT, pp. 384–388. ACL (2016)

    Google Scholar 

  29. Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural Comput. 1(2), 270–280 (1989)

    Article  Google Scholar 

  30. Xu, K., Qi, G., Huang, J., Wu, T.: A joint model for sentiment-aware topic detection on social media. In: Proceedings of ECAI, pp. 338–346. IOS Press (2016)

    Google Scholar 

  31. Yan, X., Guo, J., Lan, Y., Cheng, X.: A biterm topic model for short texts. In: Proceedings of WWW, pp. 1445–1456. ACM (2013)

    Google Scholar 

  32. Zarrella, G., Marsh, A.: MITRE at SemEval-2016 task 6: transfer learning for stance detection. In: Proceedings of SemEval@NAACL-HLT, pp. 458–463. ACL (2016)

    Google Scholar 

  33. Zhang, Z., Lan, M.: ECNU at SemEval 2016 task 6: relevant or not? Supportive or not? A two-step learning system for automatic detecting stance in tweets. In: Proceedings of SemEval@NAACL-HLT, pp. 451–457. ACL (2016)

    Google Scholar 

  34. Zhao, W.X., Jiang, J., Yan, H., Li, X.: Jointly modeling aspects and opinions with a MaxEnt-LDA hybrid. In: Proceedings of EMNLP, pp. 56–65. ACL (2010)

    Google Scholar 

  35. Zhao, W.X., Jiang, J., Weng, J., He, J., Lim, E.-P., Yan, H., Li, X.: Comparing Twitter and traditional media using topic models. In: Clough, P., Foley, C., Gurrin, C., Jones, G.J.F., Kraaij, W., Lee, H., Mudoch, V. (eds.) ECIR 2011. LNCS, vol. 6611, pp. 338–349. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-20161-5_34

    Chapter  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, Southeast Unversity, Nanjing, China

    Kang Xu, Sheng Bi & Guilin Qi

Authors
  1. Kang Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sheng Bi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Guilin Qi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kang Xu .

Editor information

Editors and Affiliations

  1. Griffith University, Brisbane, Queensland, Australia

    Zhe Wang

  2. Dresden University of Technology, Dresden, Germany

    Anni-Yasmin Turhan

  3. Griffith University, Brisbane, Queensland, Australia

    Kewen Wang

  4. Tianjin University, Tianjin, China

    Xiaowang Zhang

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Xu, K., Bi, S., Qi, G. (2017). Semi-supervised Stance-Topic Model for Stance Classification on Social Media. In: Wang, Z., Turhan, AY., Wang, K., Zhang, X. (eds) Semantic Technology. JIST 2017. Lecture Notes in Computer Science(), vol 10675. Springer, Cham. https://doi.org/10.1007/978-3-319-70682-5_13

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-70682-5_13

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-70681-8

  • Online ISBN: 978-3-319-70682-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation