Skip to Main content Skip to Navigation
Theses

Système coopératif de type égal-à-égal pour la recommandation : Application à la gestion et la recommandation de références bibliographiques.

Abstract : In this thesis, we explore reuse and automatic sharing of user past experiences in information retrieval tasks. The goal is to provide user with relevant recommendations according to her/his interests.
We use case-based reasoning (CBR) as learning and user experience modeling methodology. We use also pair-to-pair (P2P) architecture in order to protect user's autonomy. To illustrate our approach, we developed a pilot application COBRAS. It aims at managing and recommending bibliographical references.
Key problems are how to obtain relevant references and how to choose a set of peer agents that can provide the most relevant recommendations?
To handle both of the above mentioned problems, we are based on the analysis and the exploitation of the interaction backgrounds and users experiences. CBR methodology is used for two reasons:
a) to search, for a given user's interest, a set of appropriate peers to collaborate with.
b) to search for relevant references from the selected agents.
Document type :
Theses
Complete list of metadatas

Cited literature [103 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00299935
Contributor : Hajer Karoui <>
Submitted on : Thursday, July 17, 2008 - 2:30:43 PM
Last modification on : Monday, October 19, 2020 - 11:06:48 AM
Long-term archiving on: : Monday, May 31, 2010 - 7:11:02 PM

Identifiers

  • HAL Id : tel-00299935, version 1

Collections

Citation

Hajer Karoui. Système coopératif de type égal-à-égal pour la recommandation : Application à la gestion et la recommandation de références bibliographiques.. Informatique [cs]. Université Paris-Nord - Paris XIII, 2007. Français. ⟨tel-00299935⟩

Share

Metrics

Record views

308

Files downloads

495