Quantifying test collection quality based on the consistency of relevance judgements

Abstract

Relevance assessments are a key component for test collection-based evaluation of information retrieval systems. This paper reports on a feature of such collections that is used as a form of ground truth data to allow analysis of human assessment error. A wide range of test collections are retrospectively examined to determine how accurately assessors judge the relevance of documents. Our results demonstrate a high level of inconsistency across the collections studied. The level of irregularity is shown to vary across topics, with some showing a very high level of assessment error. We investigate possible influences on the error, and demonstrate that inconsistency in judging increases with time. While the level of detail in a topic specification does not appear to influence the errors that assessors make, judgements are significantly affected by the decisions made on previously seen similar documents. Assessors also display an assessment inertia. Alternate approaches to generating relevance judgements appear to reduce errors. A further investigation of the way that retrieval systems are ranked using sets of relevance judgements produced early and late in the judgement process reveals a consistent influence measured across the majority of examined test collections. We conclude that there is a clear value in examining, even inserting, ground truth data in test collections, and propose ways to help minimise the sources of inconsistency when creating future test collections.