Advertisement

Extracting 5W from Baidu Hot News Search Words for Societal Risk Events Analysis

  • Nuo Xu
  • Xijin TangEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11242)

Abstract

Nowadays risk events occur more frequently than ever in China during the critical periods of social and economic transformation and spread rapidly via a variety of social media, which have impacts on social stability. Online societal risk perception is acquired by mapping online community concerns into respective societal risks. What we concern is how to recognize and describe societal risk events in a formal and structured way. So to get a structured view of those risk events, we propose an event extraction framework on HNSW including 5 elements, namely where, who, when, why, and what (5W). The task for extracting 5W of risk events is converted into different machine learning tasks. Three methods are explored to tackle the extraction tasks. The framework of 5W extraction on the basis of online concerns can not only timely access to societal risk perception but also expose the events by a structured image, which is of great help for social management to monitor online public opinion timely and efficiently.

Keywords

5W Societal risk perception Baidu hot news search words Conditional random fields TextRank Risk-labeled keywords 

Notes

Acknowledgement

This research is supported by National Key Research and Development Program of China (2016YFB1000902) and National Natural Science Foundation of China (61473284 & 71731002).

References

  1. 1.
    Ball, D.J., Boehmer-Christiansen, S.: Societal concerns and risk decisions. J. Hazard. Mater. 144, 556–563 (2007)CrossRefGoogle Scholar
  2. 2.
    Zheng, R., Shi, K., Li, S.: The influence factors and mechanism of societal risk perception. In: Zhou, J. (ed.) Complex 2009. LNICST, vol. 5, pp. 2266–2275. Springer, Heidelberg (2009).  https://doi.org/10.1007/978-3-642-02469-6_104CrossRefGoogle Scholar
  3. 3.
    Dong, Y.H., Chen, H., Tang, X.J., Qian, W.N., Zhou, A.Y.: Prediction of social mood on Chinese societal risk perception. In: Proceedings of International Conference on Behavioral, Economic and Socio-Cultural Computing, pp. 102–108 (2015)Google Scholar
  4. 4.
    Tang, X.J.: Applying search words and BBS posts to societal risk perception and harmonious society measurement. In: Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, pp. 2191–2196 (2013)Google Scholar
  5. 5.
    Xu, N., Tang, X.: Societal risk and stock market volatility in china: a causality analysis. In: Chen, J., Theeramunkong, T., Supnithi, T., Tang, X. (eds.) KSS 2017. CCIS, vol. 780, pp. 175–185. Springer, Singapore (2017).  https://doi.org/10.1007/978-981-10-6989-5_15CrossRefGoogle Scholar
  6. 6.
    Tang, X.J.: Exploring on-line societal risk perception for harmonious society measurement. J. Syst. Sci. Syst. Eng. 22, 469–486 (2013)CrossRefGoogle Scholar
  7. 7.
    Hu, Y., Tang, X.: Using support vector machine for classification of Baidu hot word. In: Wang, M. (ed.) KSEM 2013. LNCS (LNAI), vol. 8041, pp. 580–590. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-39787-5_49CrossRefGoogle Scholar
  8. 8.
    Zhou, Y.J., Xu, B., Xu, J.M., Yang, L., Li, C.L.: Compositional recurrent neural networks for Chinese short text classification. In: International Conference on Web Intelligence, pp. 137–144 (2017)Google Scholar
  9. 9.
    Wang, P., Xu, B., Xu, J.M., et al.: Semantic expansion using word embedding clustering and convolutional neural network for improving short text classification. Neurocomputing 174, 806–814 (2016)CrossRefGoogle Scholar
  10. 10.
    Li, H., Ji, H., Zhao, L.: Social event extraction: task, challenges and techniques. In: Proceedings of International Conference on Advances in Social Networks Analysis and Mining, pp. 526–532. IEEE (2015)Google Scholar
  11. 11.
    Zhao, Y.Y., Qin, B., Che, W.X., Liu, T.: Research on Chinese event extraction. J. Chin. Inf. Process. 22, 3–8 (2008). (in Chinese)CrossRefGoogle Scholar
  12. 12.
    Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning, ICML, vol. 1, pp. 282–289 (2001)Google Scholar
  13. 13.
    Zhang, C.Y.: Text categorization model based on conditional random fields. Comput. Technol. Dev. 21, 77–80 (2011)Google Scholar
  14. 14.
    Zhao, J., Liu, K., Wang, G.: Adding redundant features for CRFs-based sentence sentiment classification. In: Proceedings of Conference on Empirical Methods in Natural Language, pp. 117–126 (2008)Google Scholar
  15. 15.
    Sudhof, M., Goméz Emilsson, A., Maas, A.L., Potts, C.: Sentiment expression conditioned by affective transitions and social forces. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1136–1145 (2014)Google Scholar
  16. 16.
    Li, T.T., Ji, D.H.: Sentiment analysis of micro-blog based on SVM and CRF using various combinations of features. Appl. Res. Comput. 32, 978–981 (2015)Google Scholar
  17. 17.
    Mihalcea, R., Tarau, P.: TextRank: bringing order into text. In: EMNLP, pp. 404–411(2004)Google Scholar
  18. 18.
    Liang, W., Huang, C.N.: Extracting keyphrases from Chinese news articles using textrank and query log knowledge? In: Proceedings of the 23rd Asia Conference on Language, Information and Computation, pp. 733–740 (2009)Google Scholar
  19. 19.
    Rahman, M.M., Roy, C.K.: TextRank based search term identification for software change tasks. In: Proceedings of International Conference on Software Analysis, Evolution and Reengineering, pp. 540–544. IEEE (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijingChina
  2. 2.University of Chinese Academy of SciencesBeijingChina

Personalised recommendations