Étude du profil utilisateur pour la recommandation dans les folksonomies

Dans les folksonomies, les utilisateurs partagent des ressources (films, livres, sites web, etc.) en les annotant avec des tags librement choisis. Dans ce papier, nous considerons une nouvelle dimension dans une folksonomie qui contient des des informations supplementaires sur les utilisateurs. Nous definissons un degre de proximite entre deux utilisateurs comme le nombre d’informations de profil en commun entre eux et nous proposons un systeme personnalise de recommandations base sur cette definition. Les experimentations menees sur un jeu de donnees du monde reel, MOVIELENS, montrent l’utilite de la nouvelle dimension introduite et quelles informations sont les plus influentes durant le processus de recommandation.

[1]  Engelbert Mephu Nguifo,et al.  A personalized recommender system based on users' information in folksonomies , 2013, WWW.

[2]  Andreas Hotho,et al.  Discovering shared conceptualizations in folksonomies , 2008, J. Web Semant..

[3]  Peter Mika.  Ontologies Are Us: A Unified Model of Social Networks and Semantics , 2005, International Semantic Web Conference.

[4]  Alejandro Bellogín,et al.  A comparative study of heterogeneous item recommendations in social systems , 2013, Inf. Sci..

[5]  Bing Wang,et al.  Personalized Tag Recommendation Using Social Contacts , 2011 .

[6]  Giovanni Quattrone,et al.  A query expansion and user profile enrichment approach to improve the performance of recommender systems operating on a folksonomy , 2010, User Modeling and User-Adapted Interaction.

[7]  Sarabjot Singh Anand,et al.  Personalised Tag Recommendation , 2009 .

[8]  Markus Strohmaier,et al.  Understanding why users tag: A survey of tagging motivation literature and results from an empirical study , 2012, J. Web Semant..

[9]  Engelbert Mephu Nguifo,et al.  Towards more targeted recommendations in folksonomies , 2015, Social Network Analysis and Mining.

[10]  Andreas Hotho,et al.  Information Retrieval in Folksonomies: Search and Ranking , 2006, ESWC.

[11]  Giovanni Semeraro,et al.  Recommending Smart Tags in a Social Bookmarking System , 2007 .

[12]  M. Lipczak,et al.  Tag Recommendation for Folksonomies Oriented towards Individual Users , 2008 .

[13]  Richi Nayak,et al.  Personalized recommender system based on item taxonomy and folksonomy , 2010, CIKM.

[14]  Andreas Hotho,et al.  Tag Recommendations in Folksonomies , 2007, LWA.

[15]  Yiu-Kai Ng,et al.  Predicting the ratings of multimedia items for making personalized recommendations , 2012, SIGIR '12.

[16]  Panagiotis Symeonidis,et al.  MusicBox: Personalized Music Recommendation Based on Cubic Analysis of Social Tags , 2010, IEEE Transactions on Audio, Speech, and Language Processing.

[17]  Tereza Iofciu,et al.  Finding Communities of Practice from User Profiles Based on Folksonomies , 2006, EC-TEL Workshops.

[18]  Jonathan L. Herlocker,et al.  Evaluating collaborative filtering recommender systems , 2004, TOIS.

[19]  Jean-François Boulicaut,et al.  Closed patterns meet n-ary relations , 2009, TKDD.