Simple time-aware and social-aware user similarity for a KNN-based recommender system

Abstract : In this paper we report the results of the experiment carried out by our institutions for participating in the track 1 of the the 2011 CAMRa challenge workshop. We ran some variations of a traditional user-based neighborhood recommender system based on two simple ideas: (1) Force the inclusion of household members into the neighborhood of the user and (2) increase the similarity of users that use the system if they use the system at similar time slots. The approaches are evaluated using the MAP, P@5, P@10 and AUC metrics. Results show that a small improvement is achieved on of the chosen metrics when comparing the social and time strategies to a traditional KNN approach.
Type de document :
Communication dans un congrès
2nd Challenge on Context-Aware Movie Recommendation (CAMRa 2011), Oct 2011, Chicago, United States. pp.36-38 <http://dl.acm.org/event.cfm?id=RE587&CFID=640218233&CFTOKEN=24699461>. <10.1145/2096112.2096119>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01342285
Contributeur : Michel Riveill <>
Soumis le : mardi 5 juillet 2016 - 16:22:14
Dernière modification le : mercredi 6 juillet 2016 - 01:04:53

Identifiants

Collections

Citation

Andrés Moreno, Harold Castro, Michel Riveill. Simple time-aware and social-aware user similarity for a KNN-based recommender system. 2nd Challenge on Context-Aware Movie Recommendation (CAMRa 2011), Oct 2011, Chicago, United States. pp.36-38 <http://dl.acm.org/event.cfm?id=RE587&CFID=640218233&CFTOKEN=24699461>. <10.1145/2096112.2096119>. <hal-01342285>

Partager

Métriques

Consultations de la notice

34