Revisiting the relationship between document length and relevance

David E. Losada, Leif Azzopardi, Mark Baillie

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

6 Citations (Scopus)

Abstract

The scope hypothesis in Information Retrieval (IR) states that a relationship exists between document length and relevance, such that the likelihood of relevance increases with document length. A number of empirical studies have provided statistical evidence supporting the scope hypothesis. However, these studies make the implicit assumption that modern test collections are complete (i.e. all documents are assessed for relevance). As a consequence the observed evidence is misleading. In this paper we perform a deeper analysis of document length and relevance taking into account that test collections are incomplete. We first demonstrate that previous evidence supporting the scope hypothesis was an artefact of the test collection, where there is a bias towards longer documents in the pooling process. We evaluate whether this length bias affects system comparison when using incomplete test collections. The results indicate that test collections are problematic when considering MAP as a measure of effectiveness but are relatively robust when using bpref. The implications of the study indicate that retrieval models should not be tuned to favour longer documents, and that designers of new test collections should take measures against length bias during the pooling process in order to create more reliable and robust test collections.
Original languageEnglish
Title of host publicationCIKM '08 Proceedings of the 17th ACM Conference on Information and Knowledge Management
Place of PublicationNew York, NY, USA
Pages419-428
Number of pages10
DOIs
Publication statusPublished - 26 Oct 2008

Keywords

  • document length
  • relevance
  • pooling
  • information retrieval

Cite this

Losada, D. E., Azzopardi, L., & Baillie, M. (2008). Revisiting the relationship between document length and relevance. In CIKM '08 Proceedings of the 17th ACM Conference on Information and Knowledge Management (pp. 419-428). https://doi.org/10.1145/1458082.1458139