HMM-CARe : hidden Markov models for context-aware tag recommendation in folksonomies - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

HMM-CARe : hidden Markov models for context-aware tag recommendation in folksonomies

Résumé

Collaborative tagging systems allow users to manually annotate web resources with freely chosen keywords aka tags without any restriction to a certain vocabulary. The resulting collection of all these users annotations constitute the so-called folksonomy. Such systems typically provide simple tag recommendations skills to increase the number of tags assigned to resources. In this this paper, we propose a novel Hidden Markov Model (HMM) based approach, called HMM-CARE, for tags recommendation. Specifically, we extend the HMM to include user's tagging intents, formally represented as triadic concepts. Carried out experiments emphasize the relevance of our proposal and open many thriving issues
Fichier non déposé

Dates et versions

hal-01300477 , version 1 (11-04-2016)

Identifiants

Citer

Chiraz Trabelsi, Bilel Moulahi, Sadok Ben Yahia. HMM-CARe : hidden Markov models for context-aware tag recommendation in folksonomies. SAC 2012 : 27th Annual ACM Symposium on Applied Computing, Mar 2012, Trento, Italy. pp.957 - 961, ⟨10.1145/2245276.2245461⟩. ⟨hal-01300477⟩
28 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More