Semi-metric networks for recommender systems


Tiago Simas1 and Luis M. Rocha1,2,3

1Cognitive Science Program, Indiana University, Bloomington IN, USA
2School of Informatics, Indiana University, Bloomington IN, USA
3FLAD Computational Biology Collaboratorium, Instituto Gulbenkian de Ciencia, Portugal

Citation: T. Simas and L.M. Rocha [2012]."Semi-metric networks for recommender systems" (pdf). 2012 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology, pp. 175-179. DOI:10.1109/WI-IAT.2012.245

Due to mathematical notation and graphics, the full text is available in pdf. The pre-print is also available.

Abstract.

Weighted graphs obtained from co-occurrence in user-item relations lead to non-metric topologies. We use this semi-metric behavior to issue recommendations, and discuss its relationship to transitive closure on fuzzy graphs. Finally, we test the performance of this method against other item- and user-based recommender systems on the Movielens benchmark. We show that including highly semi-metric edges in our recommendation algorithms leads to better recommendations.

Keywords:recommender systems;complex networks; network theory, fuzzy graphs; fuzzy systems.


For more information contact Luis Rocha at rocha@indiana.edu. Check the Web Design Credits, for due credit.
Last Modified: January 13, 2013