Sentiment Propagation for Predicting Reputation Polarity

  • Anastasia GiachanouEmail author
  • Julio Gonzalo
  • Ida Mele
  • Fabio Crestani
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10193)


One of the core tasks of Online Reputation Monitoring is to determine whether a text mentioning the entity of interest has positive or negative implications for its reputation. A challenging aspect of the task is that many texts are polar facts, i.e. they do not convey sentiment but they do have reputational implications (e.g. A Samsung smartphone exploded during flight has negative implications for the reputation of Samsung). In this paper we explore the hypothesis that, in order to determine the reputation polarity of factual information, we can propagate sentiment from sentiment-bearing texts to factual texts that discuss the same issue. We test two approaches that implement such hypothesis: the first one is to directly propagate sentiment to similar texts, and the second one is to augment the polarity lexicon. Our results (i) confirm our propagation hypothesis, with improvements of up to 43% in weakly supervised settings and up to 59% with fully supervised methods; and (ii) indicate that building domain-specific polarity lexicons is a cost-effective strategy.


Reputation polarity Sentiment propagation 



This research was partially funded by the Swiss National Science Foundation (SNSF) under the project OpiTrack.


  1. 1.
    Agarwal, A., Xie, B., Vovsha, I., Rambow, O., Passonneau, R.: Sentiment analysis of Twitter data. In: LSM 2011, pp. 30–38. ACL (2011)Google Scholar
  2. 2.
    Amigó, E., et al.: Overview of RepLab 2013: evaluating online reputation monitoring systems. In: Forner, P., Müller, H., Paredes, R., Rosso, P., Stein, B. (eds.) CLEF 2013. LNCS, vol. 8138, pp. 333–352. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-40802-1_31 CrossRefGoogle Scholar
  3. 3.
    Amigó, E., Corujo, A., Gonzalo, J., Meij, E., de Rijke, M.: Overview of RepLab 2012: evaluating online reputation management systems. In: CLEF 2012 (2012)Google Scholar
  4. 4.
    Castellanos, A., Cigarrán, J., García-Serrano, A.: Modelling techniques for Twitter contents: a step beyond classification based approaches. In: CLEF 2013 (2013)Google Scholar
  5. 5.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. Trans. Intell. Syst. Technol. 2(3), 27:1–27:27 (2011)Google Scholar
  6. 6.
    Church, K.W., Hanks, P.: Word association norms, mutual information, and lexicography. Comput. Linguist. 16(1), 22–29 (1990)Google Scholar
  7. 7.
    Gerani, S., Carman, M., Crestani, F.: Aggregation methods for proximity-based opinion retrieval. ACM Trans. Inf. Syst. (TOIS) 30(4), 1–36 (2012)CrossRefGoogle Scholar
  8. 8.
    Giachanou, A., Crestani, F.: Like it or not: a survey of Twitter sentiment analysis methods. ACM Comput. Surv. (CSUR) 49(2), 28 (2016)CrossRefGoogle Scholar
  9. 9.
    Giachanou, A., Harvey, M., Crestani, F.: Topic-specific stylistic variations for opinion retrieval on Twitter. In: Ferro, N., Crestani, F., Moens, M.-F., Mothe, J., Silvestri, F., Nunzio, G.M., Hauff, C., Silvello, G. (eds.) ECIR 2016. LNCS, vol. 9626, pp. 466–478. Springer, Cham (2016). doi: 10.1007/978-3-319-30671-1_34 CrossRefGoogle Scholar
  10. 10.
    Hangya, V., Farkas, R.: Filtering and polarity detection for reputation management on tweets. In: CLEF 2013 (2013)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.
    Kiritchenko, S., Zhu, X., Mohammad, S.M.: Sentiment analysis of short informal texts. J. Artif. Intell. Res. 50(1), 723–762 (2014)zbMATHGoogle Scholar
  13. 13.
    Kouloumpis, E., Wilson, T., Moore, J.: Twitter sentiment analysis: the good the bad and the OMG! In: ICWSM 2011, pp. 538–541. AAAI Press (2011)Google Scholar
  14. 14.
    Mohammad, S.M., Turney, P.D.: Emotions evoked by common words and phrases: using mechanical turk to create an emotion lexicon. In: CAAGET 2010, pp. 26–34. ACL (2010)Google Scholar
  15. 15.
    Mosquera, A., Fernández, J., M. Gómez, J., Martínez-Barco, P., Moreda, P.: DLSI-Volvam at RepLab 2013: polarity classification on Twitter data. In: CLEF 2013 (2013)Google Scholar
  16. 16.
    Nielsen, F.: A new ANEW: evaluation of a word list for sentiment analysis of microblogs. In: ESWC 2011 Workshop on ‘Making Sense of Microposts’: Big Things Come in Small Packages, pp. 93–98 (2011)Google Scholar
  17. 17.
    Pak, A., Paroubek, P.: Twitter as a corpus for sentiment analysis and opinion mining. In: LREC 2010, pp. 1320–1326. ELRA (2010)Google Scholar
  18. 18.
    Pang, B., Lee, L.: Opinion mining and sentiment analysis. Found. Trends Inf. Retrieval 2(1–2), 1–135 (2008)CrossRefGoogle Scholar
  19. 19.
    Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up? Sentiment classification using machine learning techniques. In: EMNLP 2002, pp. 79–86. ACL (2002)Google Scholar
  20. 20.
    Peetz, M.H., de Rijke, M., Kaptein, R.: Estimating reputation polarity on microblog posts. Inf. Process. Manag. 52(2), 193–216 (2016)CrossRefGoogle Scholar
  21. 21.
    Perez-Rosas, V., Banea, C., Mihalcea, R.: Learning sentiment lexicons in Spanish. In: LREC 2012. ELRA (2012)Google Scholar
  22. 22.
    Saias, J.: In search of reputation assessment: experiences with polarity classification in RepLab 2013. In: CLEF 2013 (2013)Google Scholar
  23. 23.
    Spina, D., Gonzalo, J., Amigó, E.: Learning similarity functions for topic detection in online reputation monitoring. In: SIGIR 2014, pp. 527–536. ACM (2014)Google Scholar
  24. 24.
    Taboada, M., Brooke, J., Tofiloski, M., Voll, K., Stede, M.: Lexicon-based methods for sentiment analysis. Comput. Linguist. 37(2), 267–307 (2011)CrossRefGoogle Scholar
  25. 25.
    Turney, P.D.: Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In: ACL 2002, pp. 417–424. ACL (2002)Google Scholar
  26. 26.
    Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing contextual polarity in phrase-level sentiment analysis. In: HLT 2005, pp. 347–354. ACL (2005)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Anastasia Giachanou
    • 1
    Email author
  • Julio Gonzalo
    • 2
  • Ida Mele
    • 1
  • Fabio Crestani
    • 1
  1. 1.Faculty of InformaticsUniversità della Svizzera Italiana (USI)LuganoSwitzerland
  2. 2.UNED NLP & IR GroupMadridSpain

Personalised recommendations