Recommender System strategies for Social Networks

Recently user recommendation on Social Networks has gained a lot of importance as a result of the stunning success of micro-blogging services. There has been also extensive work on detecting social network communities, especially by characterizing contents and tags extracted from the social networks. Apart from a few notable exceptions, state-of-the-art approaches for user recommendation that relying only on contents show low precision due to short and noisy contents, while collaborative filtering approaches that leverage users’ social graphs lead to higher precision but data sparsity remains a relevant challenge to address. The rationale of this projects is the distinction between similar interests and similar opinions or feelings between users. Therefore, by considering the contribution of user sentiments, interesting insights into community detection and user recommendation can be identified.

Recommender systems are achieved through different strategies :

  1. User Recommender using Sentiment-Volume-Objectivity analysis;
  2. Exploiting Community Detection to improve Recommendation;
  3. Framework iSCUR: Interest and Sentiment-Based Community Detection for User Recommendation

These systems are presented in different pubblication as follows:

Publications

  • DAVIDE FELTONI GURINI, FABIO GASPARETTI, ALESSANDRO MICARELLI AND GIUSEPPE SANSONETTI. iSCUR: Interest and Sentiment-Based Community Detection for User Recommendation on Twitter. In Proc. of User Modeling, Adaptation, and Personalization, 2014 (PDF)
  • DAVIDE FELTONI GURINI, FABIO GASPARETTI, ALESSANDRO MICARELLI AND GIUSEPPE SANSONETTI. A Sentiment-based Approach to Twitter  User Recommendation. Proc. of the 5th ACM RecSys workshop on Recommender systems and the social web (RSWEB 2013) (PDFBibtex, ©ACM, 2013. This is the author’s version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version will be published in ACM DL)
  • GIULIANO ARRU, DAVIDE FELTONI GURINI, FABIO GASPARETTI, ALESSANDRO MICARELLI AND GIUSEPPE SANSONETTI. Signal-Based User Recommendation on Twitter. Proc. 4th International Workshop on Social Recommender Systems (SRS 2013) (PDFBibtex)

Created

Comments are closed.