On the impact of domain expertise on query formulation, relevance assessment and retrieval performance in clinical settings - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Information Processing and Management Année : 2017

On the impact of domain expertise on query formulation, relevance assessment and retrieval performance in clinical settings

Résumé

The large volumes of medical information available on the web may provideanswers for a wide range of users attempting to solve health-related problems.While experts generally utilize reliable resources for diagnosis searchand professional development, novices utilize dierent (social) web resourcesto obtain information that helps them manage their health or the health ofpeople who they care for. A diverse number of related search topics addressclinical diagnosis, advice searching, information sharing, connecting with experts,etc. This article focuses on the extent to which expertise can impactclinical query formulation, document relevance assessment and retrieval performancein the context of tailoring retrieval models and systems to expertsvs. non-experts. The results show that medical domain expertise 1) plays animportant role in the lexical representations of information needs; 2) significantlyinfuences the perception of relevance even among users with similarlevels of expertise and 3) reinforces the idea that a single ground truth doesn'texist, thereby leading to the variability of system rankings with respect to thelevel of user's expertise. The findings of this study presents opportunities forthe design of personalized health-related IR systems, but also for providinginsights about the evaluation of such systems.
Fichier principal
Vignette du fichier
IPM16_Rev.pdf (777.82 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01414706 , version 1 (12-12-2016)

Identifiants

Citer

Lynda Tamine, Cécile Chouquet. On the impact of domain expertise on query formulation, relevance assessment and retrieval performance in clinical settings. Information Processing and Management, 2017, 53, pp.332 - 350. ⟨10.1016/j.ipm.2016.11.004⟩. ⟨hal-01414706⟩
484 Consultations
245 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More