Enhancing Social Recommendation with Sentiment Communities

  • Davide Feltoni GuriniEmail author
  • Fabio Gasparetti
  • Alessandro Micarelli
  • Giuseppe Sansonetti
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9419)


Among the various recommender systems proposed in the literature, there is an increase in relevance and number of those that suggest users of possible interest to the target user. In this article, we propose a new algorithm for realizing user recommenders, named SCORES (Sentiment COmmunities REcommender System). This algorithm relies on the identification of sentiment communities in which, for each topic cited by the user, we consider not only the relative sentiment, but also the volume and the objectivity of contents generated by him. The graph related to each topic is obtained by considering the Tanimoto similarity between users. The recommendation process occurs by clustering the obtained graph to detect latent communities, and suggesting to the target user the most similar K users based on tie strength measures. A comparative analysis between SCORES and some state-of-the-art approaches shows the benefits in term of performance.


Sentiment analysis Recommender system Community detection 


  1. 1.
    Abel, F., Gao, Q., Houben, G.-J., Tao, K.: Analyzing user modeling on twitter for personalized news recommendations. In: Konstan, J.A., Conejo, R., Marzo, J.L., Oliver, N. (eds.) UMAP 2011. LNCS, vol. 6787, pp. 1–12. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  2. 2.
    Arru, G., Feltoni Gurini, D., Gasparetti, F., Micarelli, A., Sansonetti, G.: Signal-based user recommendation on twitter. In: Proceedings of the 22nd International Conference on World Wide Web Companion, pp. 941–944 (2013)Google Scholar
  3. 3.
    Chen, J., Geyer, W., Dugan, C., Muller, M., Guy, I.: Make new friends, but keep the old: recommending people on social networking sites. In: Proceedings of the 27th International Conference on Human Factors in Computing Systems, CHI 2009, pp. 201–210. ACM, New York (2009)Google Scholar
  4. 4.
    Feltoni Gurini, D., Gasparetti, F., Micarelli, A., Sansonetti, G.: A sentiment-based approach to twitter user recommendation. In: Proceedings of the 5th ACM RecSys Workshop on Recommender Systems and the Social Web (2013)Google Scholar
  5. 5.
    Granovetter, M.: The strength of weak ties. Am. J. Sociol. 78(6), 1360–1380 (1973)CrossRefGoogle Scholar
  6. 6.
    John, H., Mike, B., Barry, S.: Recommending twitter users to follow using content and collaborative filtering approaches. In: Proceedings of the 4th ACM Conference on Recommender Systems, RecSys 2010, 26–30 September 2010Google Scholar
  7. 7.
    Tanimoto, T.T.: An elementary mathematical theory of classification and prediction. IBM Internal Report (1957)Google Scholar
  8. 8.
    Thelwall, M., Buckley, K., Paltoglou, G.: Sentiment in twitter events. J. Am. Soc. Inf. Sci. Technol. 62(2), 406–418 (2011). CrossRefGoogle Scholar
  9. 9.
    Tumasjan, A., Sprenger, T., Sandner, P., Welpe, I.: Predicting elections with twitter: what 140 characters reveal about political sentiment. In: Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, pp. 178–185 (2010)Google Scholar
  10. 10.
    Xu, K., Li, J., Liao, S.S.: Sentiment community detection in social networks. In: Proceedings of the 2011 iConference, pp. 804–805. ACM, New York (2011)Google Scholar
  11. 11.
    Yuan, G., Murukannaiah, P.K., Zhang, Z., Singh, M.P.: Exploiting sentiment homophily for link prediction. In: Proceedings of the 8th ACM Conference on Recommender Systems, RecSys 2014, pp. 17–24. ACM, New York (2014)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Davide Feltoni Gurini
    • 1
    Email author
  • Fabio Gasparetti
    • 1
  • Alessandro Micarelli
    • 1
  • Giuseppe Sansonetti
    • 1
  1. 1.Artificial Intelligence Laboratory, Department of EngineeringRoma Tre UniversityRomeItaly

Personalised recommendations