A Sentiment and Topic Model with Timeslice, User and Hashtag for Posts on Social Media

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 784)

Abstract

Nowadays plenty of user-generated posts, e.g., tweets, are published on social media and the posts imply the public’s opinions towards various topics. Joint sentiment/topic models are widely applied in detecting sentiment-aware topics on the lengthy documents. However, the characteristics of posts, i.e., short texts, on social media pose new challenges: (1) context sparsity problem of posts makes traditional sentiment-topic models infeasible; (2) conventional sentiment-topic models are designed for flat documents without structure information, while publishing users, publishing timeslices and hashtags of posts provide rich structure information for modeling these posts. In this paper, we firstly devise a method to mine potential hashtags, based on explicit hashtags, to further enrich structure information for posts, then we propose a novel Sentiment Topic Model for Posts (STMP) which aggregates posts with the structure information, i.e., timeslices, users and hashtags, to alleviate the context sparsity problem. Experiments on Twitter7 show STMP outperforms previous models in sentiment-aware topic extraction.

Keywords

Topic model Sentiment analysis Topic extraction Short text 

Notes

Acknowledgements

This work is supported in part by the National Natural Science Foundation of China (NSFC) under Grant No. 61672153, the 863 Program under Grant No. 2015AA015406 and the Fundamental Research Funds for the Central Universities and the Research Innovation Program for College Graduates of Jiangsu Province under Grant No. KYLX16_0295.

References

  1. 1.
    Chen, Z., Mukherjee, A., Liu, B., Hsu, M., Castellanos, M., Ghosh, R.: Leveraging multi-domain prior knowledge in topic models. In: Proceedings of IJCAI, pp. 2071–2077. AAAI (2013)Google Scholar
  2. 2.
    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
  3. 3.
    Jo, Y., Oh, A.H.: Aspect and sentiment unification model for online review analysis. In: Proceedings of WSDM, pp. 815–824. ACM (2011)Google Scholar
  4. 4.
    Lin, C., He, Y.: Joint sentiment/topic model for sentiment analysis. In: Proceedings of CIKM, pp. 375–384. ACM (2009)Google Scholar
  5. 5.
    Mukherjee, S., Basu, G., Joshi, S.: Joint author sentiment topic model. In: SDM, pp. 370–378. SIAM (2014)Google Scholar
  6. 6.
    Rong, X.: Word2Vec parameter learning explained. arXiv preprint arXiv:1411.2738 (2014)
  7. 7.
    Wang, Y., Liu, J., Huang, Y., Feng, X.: Using hashtag graph-based topic model to connect semantically-related words without co-occurrence in microblogs. IEEE Trans. Knowl. Data Eng. 28(7), 1919–1933 (2016)CrossRefGoogle Scholar
  8. 8.
    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
  9. 9.
    Zhang, Q., Gong, Y., Sun, X., Huang, X.: Time-aware personalized hashtag recommendation on social media. In: Proceedings of COLING, pp. 203–212. ACL (2014)Google Scholar
  10. 10.
    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 CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2017

Authors and Affiliations

  1. 1.Department of Computer ScienceSoutheast UnversityNanjingChina

Personalised recommendations