Detecting Communities by Sentiment Analysis of Controversial Topics

  • Kangwon Seo
  • Rong PanEmail author
  • Aleksey Panasyuk
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9708)


Controversial topics, particularly political topics, often provoke very different emotions among different communities. By detecting and analyzing communities formed around these controversial topics we can paint a picture of how polarized a country is and how these communities evolved over time. In this research, we made use of Internet data from Twitter, one of the most popular online social media sites, to identify a controversial topic of interest and the emotions expressed towards the topic. Communities were formed based on Twitter users’ sentiments towards the topic. In addition, the network structure of these communities was utilized to reveal those Twitter users that played important roles in their respective communities.


Topic modeling Sentiment analysis Twitter Social network analysis 



The authors thank Sue E. Kase and Liz Bowman at the Army Research Lab for their help in getting access to the Egypt data. The views expressed in this paper do not represent the views of the U.S. government.


  1. 1.
    Ajzen, I.: Attitudes, Personality, and Behavior. Dorsey Press, Chicago (1988)Google Scholar
  2. 2.
    Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)zbMATHGoogle Scholar
  3. 3.
    Borge-Holthoefer, J., Magdy, W., Darwish, K., Weber, I.: Content and network dynamics behind egyptian political polarization on twitter. In: CSCW 2015, pp. 700–711. ACM (2015)Google Scholar
  4. 4.
    Bruns, A., Highfield, T., Burgess, J.: The arab spring and social media audiences english and arabic twitter users and their networks. Am. Behav. Sci. 57(7), 871–898 (2013)CrossRefGoogle Scholar
  5. 5.
    Conover, M.D., Gonalves, B., Ratkiewicz, J., Flammini, A., Menczer, F.: Predicting the political alignment of twitter users. In: PASSAT/SocialCom 2011, pp. 192–199. IEEE (2011)Google Scholar
  6. 6.
    Du, N., Wu, B., Pei, X., Wang, B., Xu, L.: Community detection in large-scale social networks. In: WebKDD/SNA-KDD 2007, pp. 16–25. ACM (2007)Google Scholar
  7. 7.
    Feinerer, I., Meyer, D., Hornik, K.: Text mining infrastructure in R. J. Stat. Softw. 25(5), 1–54 (2008)CrossRefGoogle Scholar
  8. 8.
    Fortunato, S.: Community detection in graphs. Phys. Rep. 485, 75 (2010)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Grün, B., Hornik, K.: topicmodels: An R package for fitting topic models. J. Stat. Softw. 40(13), 1–30 (2011)CrossRefGoogle Scholar
  10. 10.
    Hong, L., Davison, B.D.: Empirical study of topic modeling in twitter. In: SOMA 2010, pp. 80–88. ACM (2010)Google Scholar
  11. 11.
    Hu, M., Liu, B.: Mining and summarizing customer reviews. In: KDD 2004, pp. 168–177. ACM (2004)Google Scholar
  12. 12.
    Liu, B.: Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers, San Rafael (2012)Google Scholar
  13. 13.
    Lotan, G., Graeff, E., Ananny, M., Gaffney, D., Pearce, I.: The arab spring—the revolutions were tweeted: information flows during the 2011 tunisian and egyptian revolutions. Int. J. Commun. 5, 31 (2011)Google Scholar
  14. 14.
    Marwick, B.: Discovery of emergent issues and controversies in anthropology using text mining, topic modeling, and social network analysis of microblog content. In: Data Mining Applications with R, p. 514. Academic Press, New York (2014)Google Scholar
  15. 15.
    Mehrotra, R., Sanner, S., Buntine, W., Xie, L.: Improving LDA topic models for microblogs via tweet pooling and automatic labeling. In: SIGIR 2013, pp. 889–892. ACM (2013)Google Scholar
  16. 16.
    Newman, M.E.J., Girvan, M.: Finding and evaluating community structure in networks. Phys. Rev. E69(2), 026113 (2004)Google Scholar
  17. 17.
    O’Brien, S., Shellman, S.: Effects of Emotions on Dissident and Government Behavior. Strategic Analysis Enterprise (SAE) Inc., Williamsburg, VA (2013)Google Scholar
  18. 18.
    Papadopoulos, S., Kompatsiaris, Y., Vakali, A., Spyridonos, P.: Community detection in social media. Data Min. Knowl. Disc. 24(3), 515–554 (2012)CrossRefGoogle Scholar
  19. 19.
    Parau, P., Stef, A., Lemnaru, C., Dinsoreanu, M., Potolea, R.: Using community detection for sentiment analysis. In: ICCP 2013, pp. 51–54. IEEE (2013)Google Scholar
  20. 20.
    Qi, G.J., Aggarwal, C.C., Huang, T.: Community detection with edge content in social media networks. In: ICDE 2012, pp. 534–545. IEEE (2012)Google Scholar
  21. 21.
    Ramage, D., Dumais, S.T., Liebling, D.J.: Characterizing microblogs with topic models. In: ICWSM 2010, p. 1 (2010)Google Scholar
  22. 22.
    Rosenthal, S., Nakov, P., Kiritchenko, S., Mohammad, S.M., Ritter, A., Stoyanov, V.: SemEval-2015 Task 10: Sentiment analysis in twitter. In: SemEval 2015, pp. 451–463 (2015)Google Scholar
  23. 23.
    Rosvall, M., Bergstrom, C.T.: Maps of random walks on complex networks reveal community structure. PNAS 105(4), 1118–1123 (2008)CrossRefGoogle Scholar
  24. 24.
    Strapparava, C., Valitutti, A.: WordNet affect: an affective extension of wordnet. In: LREC, vol. 4, pp. 1083–1086 (2004)Google Scholar
  25. 25.
    Tang, L., Liu, H.: Community detection and mining in social media. Synth. Lect. Data Min. Knowl. Discovery 2(1), 1–137 (2010)CrossRefGoogle Scholar
  26. 26.
    Xie, R., Li, C.: Lexicon construction: A topic model approach. In: ICSAI 2012, pp. 2299–2303. IEEE (2012)Google Scholar
  27. 27.
    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)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.School of Computing, Informatics, and Decision Systems EngineeringArizona State UniversityTempeUSA
  2. 2.Air Force Research LabRomeUSA

Personalised recommendations