Semantic clustering of users based on shared conceptualizations in folksonomies

Sana Hamdi (1) , Alda Lopes Gancarski (2, 3, 4) , Amel Bouzeghoub (5, 2, 3, 4) , Sadok Ben Yahia (1)

1 FST - Département d'informatique
2 TSP - INF - Département Informatique
3 SAMOVAR - Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux
4 CNRS - Centre National de la Recherche Scientifique
5 ACMES-SAMOVAR - Architecture, Cloud continuum, formal Models, artificial intElligence and Services in distributed computing

Folksonomy systems and social bookmarking tools are rapidly spreading on the Web. Their steady increase reveals a trend towards a more dynamic and interactive space, in which users can individually assign terms to online resources. Even though users find tagging easy to use and understand, they need to see, closely, users sharing same interest as them for many reasons (facilitating the information retrieval and confidentiality management, insuring privacy respect, etc.). In this paper, we introduce a new method for automatically creating a new social network, across a popular folksonomy site, where users are clustered according to their domain of interest. We semantically represent these interests by using DBPEDIA ontology as a multi-domain ontology and we propose a methodology for enriching this ontology

Domaines: Réseaux et télécommunications [cs.NI]

Sana Hamdi, Alda Lopes Gancarski, Amel Bouzeghoub, Sadok Ben Yahia. Semantic clustering of users based on shared conceptualizations in folksonomies. CASoN 2011 : 3rd International Conference on Computational Aspects of Social Networks, Oct 2011, Salamanca, Spain. pp.201 - 206, ⟨10.1109/CASON.2011.6085944⟩. ⟨hal-01302227⟩