Automatic Expansion of a Social Network Using Sentiment Analysis

  • Hristo Tanev
  • Bruno Pouliquen
  • Vanni Zavarella
  • Ralf Steinberger
Part of the Annals of Information Systems book series (AOIS, volume 12)


In this chapter, we present an approach to learn a signed social network automatically from online news articles. The vertices in this network represent people and the edges are labeled with the polarity of the attitudes among them (positive, negative, and neutral). Our algorithm accepts as its input two social networks extracted via unsupervised algorithms: (1) a small signed network labeled with attitude polarities (see Tanev, Proceedings of the MMIES’2007 Workshop Held at RANLP’2007, Borovets, Bulgaria. pp. 33–40, 2007) and (2) a quotation network, without attitude polarities, consisting of pairs of people where one person makes a direct speech statement about another person (see Pouliquen et al., Proceedings of the RANLP Conference, Borovets, Bulgaria, pp. 487–492, 2007). The algorithm which we present here finds pairs of people who are connected in both networks. For each such pair (P1, P2) it takes the corresponding attitude polarity from the signed network and uses its polarity to label the quotations of P1 about P2. The obtained set of labeled quotations is used to train a Naïve Bayes classifier which then labels part of the remaining quotation network and adds it to the initial signed network. Since the social networks taken as the input are extracted in an unsupervised way, the whole approach including the acquisition of input networks is unsupervised.


Social Network Negative Attitude Signed Network News Article Sentiment Analysis 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



We would like to thank the whole team working on the Europe Media Monitor for providing the valuable news data. Their research and programming effort laid the foundation which made this experimental work possible.


  1. 1.
    Agrawal, R., Rajagopalan, S., Srikant, R., and Xu, Y. Mining newsgroups using networks arising from social behavior. In Proceedings of World-Wide Web Conference, Budapest, Hungary, pp. 529–535, 2003.Google Scholar
  2. 2.
    Allison, B. Sentiment detection using lexically-based classifiers. In To Appear in Proceedings of TSD’2008 Brno, Czech Republic, 2008.Google Scholar
  3. 3.
    Alrahabi, M. and Desclés, J.P. Automatic annotation of direct reported speech in Arabic and French, according to semantic map of enunciative modalities. In Proceedings of GoTAL conference, Gothenburg, Sweden, pp. 40–51, 2008.Google Scholar
  4. 4.
    Crockett, W.H. Inferential rules in the learning and recall of patterns of sentiments. Journal of Personality, 47(4):658–676, 1979.CrossRefGoogle Scholar
  5. 5.
    Dave, K., Lawrence, S., and Pennock, D.M. Mining the peanut gallery: Opinion extraction and semantic classification of product reviews. In Proceedings of World-Wide Web Conference, Budapest, Hungary, pp. 519–528, 2003.Google Scholar
  6. 6.
    Davis, J.A. Clustering and structural balance in graphs. Human Relations 30:181–187, 1967.CrossRefGoogle Scholar
  7. 7.
    Davis, J.A. The Davis/Holland/Leinhardt studies: An overview. In P.W. Holland and S. Leinhardt (eds), Perspectives on Social Network Research, New York, NY: Academic, pp. 51–62, 1979.Google Scholar
  8. 8.
    Efron, M. Cultural orientation: Classifying subjective documents by cociation [sic] analysis. In Proceedings of the AAAI Fall Symposium on Style and Meaning in Language, Art, Music, and Design, Washington, DC, pp. 41–48, 2004.Google Scholar
  9. 9.
    Hatzivassiloglou, V. and McKeown, K. Predicting the semantic orientation of adjectives. In Proceedings of the Joint ACL/EACL Conference, Madrid, Spain, pp. 174–181, 1997.Google Scholar
  10. 10.
    Hatzivassiloglou, V. and Wiebe, J. Effects of adjective orientation and gradability on sentence subjectivity. In Proceedings of the International Conference on Computational Linguistics, Saarbrücken, Germany, pp. 299–305, 2000.Google Scholar
  11. 11.
    Kim, S.M. and Hovy, E.H. Identifying and analyzing judgment opinions. In Proceedings of the HLT-NAACL conference, New York, NY, pp. 200–207,2006.Google Scholar
  12. 12.
    Knoke, D. Political Networks: The Structural Perspective. New York, NY: Cambridge University Press, 2003.Google Scholar
  13. 13.
    Krestel, R., Witte, R., and Bergler, S. Minding the source: Automatic tagging of reported speech in newspaper articles. In Proceedings of LREC conference, Marrakech, Morocco, 2008.Google Scholar
  14. 14.
    Mihalcea, R., Banea, C., and Wiebe, J. Learning multilingual subjective language via cross-lingual projections. In Proceedings of the ACL Conference, Prague, Czech Republic, pp. 976–983, 2007.Google Scholar
  15. 15.
    Montejo-Ráez, A., Ureña-López, L.A., and Steinberger, R. Text categorization using bibliographic records: Beyond document content. Procesamiento del Lenguaje Natural, 35: 119–126, 2005.Google Scholar
  16. 16.
    Mullen, T. and Malouf, R. Taking sides: User classification for informal online political discourse. Internet Research, 18:177–190, 2008.CrossRefGoogle Scholar
  17. 17.
    Pang, B. and Lee, L. Opinion mining and sentiment analysis. Foundations and Trends in Information Retrieval, 2(1–2):1–135, 2008.CrossRefGoogle Scholar
  18. 18.
    Pang, B., Lee, L., and Vaithyanathan, V. Thumbs up? Sentiment classification using machine learning techniques. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Morristown, NJ, pp. 79–86, 2002.Google Scholar
  19. 19.
    Pouliquen, B., Steinberger, R., and Best, C. Automatic detection of quotations in multilingual news. In Proceedings of the RANLP Conference, Borovets, Bulgaria, pp. 487–492, 2007.Google Scholar
  20. 20.
    Pouliquen, B., Tanev, H., and Atkinson, M. Extracting and learning social networks out of multilingual news. In Proceedings of the SocNet workshop, Skalica, Slovakia, pp. 13–16, 2008.Google Scholar
  21. 21.
    Riloff, E. and Wiebe, J. Learning extraction patterns for subjective expressions. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Morristown, NJ, pp. 105–112, 2003.Google Scholar
  22. 22.
    Steinberger, R., Pouliquen, B., and Ignat, C. Using language-independent rules to achieve high multilinguality in Text Mining. In F. Fogelman-Soulié, D. Perrotta, J. Piskorski and R. Steinberger (eds). Mining Massive Data Sets for Security, pp. 217–240. Amsterdam: IOS Press, 2008.Google Scholar
  23. 23.
    Tanev, H. Unsupervised learning of social networks from a multiple-source news corpus. In Proceedings of the MMIES’2007 Workshop Held at RANLP’2007, Borovets, Bulgaria. pp. 33–40, 2007.Google Scholar
  24. 24.
    Turney, P. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In Proceedings of the Association for Computational Linguistics, Philadelphia, PA, pp. 417–424, 2002.Google Scholar
  25. 25.
    Wasserman, S. and Faust, K. Social network analysis: Methods and applications. Cambridge: Cambridge University Press, 2008.Google Scholar
  26. 26.
    Wilson, T., Wiebe, J., and Hwa, R. Just how mad are you? Finding strong and weak opinion clauses. Computational Intelligence, 22(2):73–99, 2006.CrossRefGoogle Scholar
  27. 27.
    Yang, B., Cheung, W., and Liu, J. Community mining from signed social networks. Transactions on Knowledge and Data Engineering 10:1333–1348, 2007.CrossRefGoogle Scholar
  28. 28.
    Yu, H. and Hatzivassiloglou, V. Towards answering opinion questions: Separating facts from opinions and identifying the polarity of opinion sentences. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, Morristown, NJ, 129–136, 2003.Google Scholar

Copyright information

© Springer US 2010

Authors and Affiliations

  • Hristo Tanev
    • 1
  • Bruno Pouliquen
    • 2
  • Vanni Zavarella
    • 1
  • Ralf Steinberger
    • 1
  1. 1.IPSC, Joint Research Centre – European CommissionIspraItaly
  2. 2.World Intellectual Property OrganizationGenevaSwitzerland

Personalised recommendations