Current Status of the Evaluation of Information Retrieval

  • Authors:

  • Yuri Kagolovsky;Jochen R. Moehr

  • Affiliations:

  • School of Health Information Science, University of Victoria, P.O. Box 3050, Victoria, British Columbia, Canada V8W 3P5/ ykagolov@uvic.ca;School of Health Information Science, University of Victoria, P.O. Box 3050, Victoria, British Columbia, Canada V8W 3P5

  • Venue:
  • Journal of Medical Systems
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

This is the second in the series of the articles on an application of the systems analytic approach to evaluation of information retrieval (IR). In the previous article a historical overview of IR was presented and existing terminological problems associated with IR were identified and discussed. In the presented article the current status of IR evaluation is summarized, and different evaluation approaches are discussed. The Cranfield evaluation model and the most often used relevance-based measures of recall and precision are explained, and their problems are presented. Possible evaluation alternatives to the Cranfield model are discussed, and the case for a systems analytic approach to IR is summarized.