The use of Linked Data datasets poses new challenges and issues in the development of next-generation systems for recommendation. In this chapter, we present MORE (MOREthan MOvie REcommendation), a Facebook -semantic application that recommends movies to the user by using information coming both from her profile and from semantic datasets. MORE exploits the power of social knowledge bases in the Linked Data cloud (e.g., DBpedia ) to detect semantic affinities among movies by adopting a novel approach that computes similarities based on a semantic vector space model (sVSM). MORE is freely available as a Facebook application and has been evaluated by real users, proving the validity of our approach.
A Recommender System for Linked Data / Mirizzi, Roberto; Ragone, Azzurra; Di Noia, Tommaso; Di Sciascio, Eugenio (DATA-CENTRIC SYSTEMS AND APPLICATIONS). - In: Semantic Search over the Web / [a cura di] Roberto De Virgilio, Francesco Guerra, Yannis Velegrakis. - STAMPA. - Berlin; Heidelberg : Springer, 2012. - ISBN 978-3-642-25007-1. - pp. 311-331 [10.1007/978-3-642-25008-8_12]
A Recommender System for Linked Data
Mirizzi, Roberto;Ragone, Azzurra;Tommaso Di Noia;Eugenio Di Sciascio
2012-01-01
Abstract
The use of Linked Data datasets poses new challenges and issues in the development of next-generation systems for recommendation. In this chapter, we present MORE (MOREthan MOvie REcommendation), a Facebook -semantic application that recommends movies to the user by using information coming both from her profile and from semantic datasets. MORE exploits the power of social knowledge bases in the Linked Data cloud (e.g., DBpedia ) to detect semantic affinities among movies by adopting a novel approach that computes similarities based on a semantic vector space model (sVSM). MORE is freely available as a Facebook application and has been evaluated by real users, proving the validity of our approach.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
