This article reports our experience in developing a recommender system (RS) able to suggest relevant people to the target user. Such a RS relies on a user profile represented as a set of weighted concepts related to the user's interests. The weighting function, we named sentiment-volume-objectivity (SVO) function, takes into account not only the user's sentiment toward his/her interests, but also the volume and objectivity of related contents. A clustering technique based on modularity optimization enables us to identify the latent sentiment communities. A preliminary experimental evaluation on real-world datasets from Twitter shows the benefits of the proposed approach and allows us to make some considerations about the detected communities.
Gurini, D.F., Gasparetti, F., Micarelli, A., Sansonetti, G. (2015). Analysis of sentiment communities in online networks. In Proceedings of the International Workshop on Social Personalisation & Search co-located with the 38th Annual ACM SIGIR Conference (SIGIR 2015) (pp.17-20).
Analysis of sentiment communities in online networks
GASPARETTI, FABIO;MICARELLI, Alessandro;SANSONETTI, GIUSEPPE
2015-01-01
Abstract
This article reports our experience in developing a recommender system (RS) able to suggest relevant people to the target user. Such a RS relies on a user profile represented as a set of weighted concepts related to the user's interests. The weighting function, we named sentiment-volume-objectivity (SVO) function, takes into account not only the user's sentiment toward his/her interests, but also the volume and objectivity of related contents. A clustering technique based on modularity optimization enables us to identify the latent sentiment communities. A preliminary experimental evaluation on real-world datasets from Twitter shows the benefits of the proposed approach and allows us to make some considerations about the detected communities.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
