Thomas, Paul; Jones, Timothy; Hawking, David
Deliberate degradation of search results is a common tool in user experiments. We degrade high-quality search results by inserting non-relevant documents at different ranks. The effect of these manipulations, on a number of commonly-used metrics, is counter-intuitive: the discount functions implicit in P@k, MRR, NDCG, and others do not account for the true relationship between rank and value to the user. We propose an alternative, based on visibility data.
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.