Advertisement

Graphical Models with Content Relevance for Crucial Date Detection in Social Media Event

  • Ruifang He
  • Dongtai Ding
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11062)

Abstract

Crucial date detection from social media text streams of an event aims to select the important dates where happen the important sub-events. The crucial dates are an important part of timeline summarization. The existing work on traditional news gains candidate dates through date expressions, and then selects crucial dates. While the posts in social media usually have fewer date expressions, so this is a new challenge for date detection. We observe that (1) there is an obvious burst when an sub-event happens; (2) the lasting durations of different sub-events are different and there are some content relevances among sub-events. Therefore, we propose a graphical models with Content Relevance for crucial Date Detection in social media event (CRDD). The model treats the publishing dates set of tweet streams as candidate dates set. A graph is constructed by content relevances of tweet streams collected in different candidate dates. The content relevances integrate semantic information of sub-topics and burst property of social media event. Based on the graph, random walk model is used to rank dates. The experiments on Twitter datasets about Arab Spring show that the proposed model is effective.

Keywords

Crucial dates detection Random walk model Word embedding Social media event 

Notes

Acknowledgements

This work was supported by the National Natural Science Foundation of China (61472277). We also thank the anonymous reviewers for their valuable comments.

References

  1. 1.
    Binh Tran, G., Alrifai, M., Quoc Nguyen, D.: Predicting relevant news events for timeline summaries. In: Proceedings of the 22nd International Conference on World Wide Web, pp. 91–92. ACM (2013)Google Scholar
  2. 2.
    Blei, D.M., Lafferty, J.D.: Dynamic topic models. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 113–120. ACM (2006)Google Scholar
  3. 3.
    Chang, Y., Tang, J., Yin, D., Yamada, M., Liu, Y.: Timeline summarization from social media with life cycle models. In: IJCAI, pp. 3698–3704 (2016)Google Scholar
  4. 4.
    Chang, Y., Yamada, M., Ortega, A., Liu, Y.: Ups and downs in buzzes: life cycle modeling for temporal pattern discovery. In: 2014 IEEE International Conference on Data Mining (ICDM), pp. 749–754. IEEE (2014)Google Scholar
  5. 5.
    Gao, D., Li, W., Cai, X., Zhang, R.: Sequential summarization: a full view of Twitter trending topics. IEEE/ACM Trans. Audio Speech Lang. Process. (TASLP) 22, 293–302 (2014)CrossRefGoogle Scholar
  6. 6.
    Kessler, R., Tannier, X., Hagege, C., Moriceau, V.: Finding salient dates for building thematic timelines. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers, vol. 1, pp. 730–739. Association for Computational Linguistics (2012)Google Scholar
  7. 7.
    Marcus, A., Bernstein, M.S., Badar, O., Karger, D.R., Madden, S., Miller, R.C.: TwitInfo: aggregating and visualizing microblogs for event exploration. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 227–236. ACM (2011)Google Scholar
  8. 8.
    Mihalcea, R., Tarau, P.: TextRank: bringing order into texts. In: EMNLP, pp. 404–411 (2004)Google Scholar
  9. 9.
    Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)
  10. 10.
    Page, L., Brin, S., Motwani, R., Winograd, T.: The PageRank citation ranking: bringing order to the web. Technical report, Stanford InfoLab (1999)Google Scholar
  11. 11.
    Ramos, J., et al.: Using TF-IDF to determine word relevance in document queries. In: Proceedings of the First Instructional Conference on Machine Learning, vol. 242, pp. 133–142 (2003)Google Scholar
  12. 12.
    Reed, J.W., Jiao, Y., Potok, T.E., Klump, B.A., Elmore, M.T., Hurson, A.R.: TF-ICF: a new term weighting scheme for clustering dynamic data streams. In: 2006 5th International Conference on Machine Learning and Applications, ICMLA 2006, pp. 258–263. IEEE (2006)Google Scholar
  13. 13.
    Tran, G., Herder, E., Markert, K.: Joint graphical models for date selection in timeline summarization. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing: Long Papers, vol. 1, pp. 1598–1607 (2015)Google Scholar
  14. 14.
    Zhao, W.X., et al.: Comparing Twitter and traditional media using topic models. In: Clough, P., et al. (eds.) ECIR 2011. LNCS, vol. 6611, pp. 338–349. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-20161-5_34CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.School of Computer Science and TechnologyTianjin UniversityTianjinChina
  2. 2.Tianjin Key Laboratory of Cognitive Computing and ApplicationTianjinChina

Personalised recommendations