Feature Frequency Inverse User Frequency for Dependant Attribute to Enhance Recommendations - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Feature Frequency Inverse User Frequency for Dependant Attribute to Enhance Recommendations

Résumé

Recommender system provides relevant items to users from huge catalogue. Collaborative filtering and content-based filtering are the most widely used techniques in personalized recommender systems. Collaborative filtering uses only the user-ratings data to make predictions, while content-based filtering relies on semantic information of items for recommendation. The aim of this work is to introduce the semantic aspect of items in a collaborative filtering process in order to enhance recommendations. Many works have addressed this problem by proposing hybrid solutions. In this paper, we present another hybridization technique that predicts users preferences for items based on their inferred preferences for semantic information of items. For this, we propose a new approach to build user semantic model by using TF-IDF measure and we provide solution to reduce the dimension of data. Applying our approach to real data, the MoviesLens 1M dataset, significant improvement can be noticed compared to usage only approach, Content only approach and hybrid algorithm
Fichier principal
Vignette du fichier
ArticlePublier.pdf (150.04 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00930911 , version 1 (14-01-2014)

Identifiants

  • HAL Id : hal-00930911 , version 1

Citer

Sonia Ben Ticha, Azim Roussanaly, Anne Boyer, Khaled Bsaies. Feature Frequency Inverse User Frequency for Dependant Attribute to Enhance Recommendations. SOTICS 2013, The Third International Conference on Social Eco-Informatics, IARA, Nov 2013, Lisbonne, Portugal. pp.45-50. ⟨hal-00930911⟩
237 Consultations
501 Téléchargements

Partager

Gmail Facebook X LinkedIn More