Measuring the Effect of Discourse Structure on Sentiment Analysis

  • Baptiste Chardon
  • Farah Benamara
  • Yannick Mathieu
  • Vladimir Popescu
  • Nicholas Asher
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7817)


The aim of this paper is twofold: measuring the effect of discourse structure when assessing the overall opinion of a document and analyzing to what extent these effects depend on the corpus genre. Using Segmented Discourse Representation Theory as our formal framework, we propose several strategies to compute the overall rating. Our results show that discourse-based strategies lead to better scores in terms of accuracy and Pearson’s correlation than state-of-the-art approaches.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Asher, N., Lascarides, A.: Logics of Conversation. Cambridge University Press (2003)Google Scholar
  2. 2.
    Baldridge, J., Lascarides, A.: Annotating discourse structures for robust semantic interpretation. In: IWCS (2005)Google Scholar
  3. 3.
    Asher, N., Benamara, F., Mathieu, Y.Y.: Distilling opinion in discourse: A preliminary study. In: CoLing, pp. 7–10 (2008)Google Scholar
  4. 4.
    Taboada, M., Voll, K., Brooke, J.: Extracting sentiment as a function of discourse structure and topicality. School of Computing Science Technical Report 2008-20 (2008)Google Scholar
  5. 5.
    Heerschop, B., Goossen, F., Hogenboom, A., Frasincar, F., Kaymak, U., de Jong, F.: Polarity analysis of texts using discourse structure. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management, pp. 1061–1070 (2011)Google Scholar
  6. 6.
    Somasundaran, S.: Discourse-level relations for Opinion Analysis. PhD Thesis, University of Pittsburgh (2010)Google Scholar
  7. 7.
    Zhou, L., Li, B., Gao, W., Wei, Z., Wong, K.F.: Unsupervised discovery of discourse relations for eliminating intra-sentence polarity ambiguities. In: Proceedings of EMNLP, pp. 162–171 (2011)Google Scholar
  8. 8.
    Benamara, F., Chardon, B., Mathieu, Y., Popescu, V.: Towards context-based subjectivity analysis. In: Proceedings of the IJCNLP, pp. 1180–1188 (2011)Google Scholar
  9. 9.
    Polanyi, L., van den Berg, M.: Discourse structure and sentiment. In: Data Mining Workshops (ICDMW), pp. 97–102 (2011)Google Scholar
  10. 10.
    Trnavac, R., Taboada, M.: The contribution of nonveridical rhetorical relations to evaluation in discourse. Language Sciences 34 (3), 301–318 (2012)CrossRefGoogle Scholar
  11. 11.
    Carlson, L., Marcu, D., Okurowski, M.E.: Building a discourse-tagged corpus in the framework of rhetorical structure theory. In: van Kuppevelt, J., Smith, R. (eds.) Current Directions in Discourse and Dialogue, pp. 85–112. Kluwer Academic Publishers (2003)Google Scholar
  12. 12.
    Toprak, C., Jakob, N., Gurevych, I.: Sentence and expression level annotation of opinions in user-generated discourse. In: ACL, Morristown, NJ, USA, pp. 575–584 (2010)Google Scholar
  13. 13.
    Afantenos, S., et al.: An empirical resource for discovering cognitive principles of discourse organisation: the annodis corpus. In: LREC (2012)Google Scholar
  14. 14.
    Leung, C.W.K., Chan, S.C.F., Chung, F.L., Ngai, G.: A probabilistic rating inference framework for mining user preferences from reviews. World Wide Web 14(2), 187–215 (2011)CrossRefGoogle Scholar
  15. 15.
    Muller, P., Afantenos, S., Denis, P., Asher, N.: Constrained decoding for text-level discourse parsing. In: Proceedings of COLING (2012)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Baptiste Chardon
    • 1
    • 2
  • Farah Benamara
    • 1
  • Yannick Mathieu
    • 3
  • Vladimir Popescu
    • 1
  • Nicholas Asher
    • 1
  1. 1.IRIT-CNRSToulouse UniversityFrance
  2. 2.Synapse DéveloppementToulouseFrance
  3. 3.LLF-CNRSParis 7 UniversityFrance

Personalised recommendations