Hybrid Method for Personalized Search in Scientific Digital Libraries

Abstract : Users of information retrieval systems usually have to repeat the tedious process of searching, browsing, and refining queries until they find relevant documents. This is because different users have different information needs, but user queries are often short and, hence, ambiguous. In this paper we study personalized search in digital libraries using user profile. The search results could be re-ranked by taking into account specific information needs of different people. We study many methods for this purpose: citation-based method, content-based method and hybrid method. We conducted experiments to compare performances of these methods. Experimental results show that our approaches are promising and applicable in digital libraries.
Type de document :
Chapitre d'ouvrage
Gelbukh, Alexander. Computational Linguistics and Intelligent Text Processing, Springer Berlin / Heidelberg, p. 512 - 521, 2008, Lecture Notes in Computer Science, 〈10.1007/978-3-540-78135-6_44〉
Liste complète des métadonnées

https://hal-emse.ccsd.cnrs.fr/emse-00674985
Contributeur : Florent Breuil <>
Soumis le : mardi 28 février 2012 - 16:09:44
Dernière modification le : mercredi 29 novembre 2017 - 10:06:37

Identifiants

Citation

Thanh Trung Van, Michel Beigbeder. Hybrid Method for Personalized Search in Scientific Digital Libraries. Gelbukh, Alexander. Computational Linguistics and Intelligent Text Processing, Springer Berlin / Heidelberg, p. 512 - 521, 2008, Lecture Notes in Computer Science, 〈10.1007/978-3-540-78135-6_44〉. 〈emse-00674985〉

Partager

Métriques

Consultations de la notice

57