On Domain Expertise-based Roles in Collaborative Information Retrieval - Archive ouverte HAL Access content directly
Journal Articles Information Processing and Management Year : 2014

On Domain Expertise-based Roles in Collaborative Information Retrieval


Collaborative information retrieval involves retrieval settings in which a group of users collaborates to satisfy the same underlying need. One core issue of collaborative IR models involves either supporting collaboration with adapted tools or developing IR models for a multiple-user context and pro-viding a ranked list of documents adapted for each collaborator. In this paper, we introduce the first document-ranking model supporting collab-oration between two users characterized by roles relying on different do-main expertise levels. Specifically, we propose a two-step ranking model: we first compute a document-relevance score, taking into consideration do-main expertise-based roles. We introduce specificity and novelty factors into language-model smoothing, and then we assign, via an Expectation-Maximization algorithm, documents to the best-suited collaborator. Our experiments employ a simulation-based framework of collaborative informa-tion retrieval and show the significant effectiveness of our model at different search levels.
Fichier principal
Vignette du fichier
2014_IPM_STB.pdf (917.38 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01118658 , version 2 (28-01-2015)
hal-01118658 , version 1 (19-02-2015)





Laure Soulier, Lynda Tamine, Wahiba Bahsoun. On Domain Expertise-based Roles in Collaborative Information Retrieval. Information Processing and Management, 2014, 50 (5), pp.752-774. ⟨10.1016/j.ipm.2014.04.002⟩. ⟨hal-01118658v2⟩
193 View
255 Download



Gmail Facebook X LinkedIn More