A universal method of information retrieval evaluation: the "missing" link M and the universal IR surface

Abstract

The paper shows that the present evaluation methods in information retrieval (basically recall R and precision P and in some cases fallout F) lack universal comparability in the sense that their values depend on the generality of the IR problem. A solution is given by using all "parts" of the database, including the non-relevant documents and also the notretrieved documents. It turns out that the solution is given by introducing the measure M being the fraction of the not-retrieved documents that are relevant (hence the "miss" measure). We prove that - independent of the IR problem or of the IR action - the quadruple (P,R,F,M) belongs to a universal IR surface, being the same for &l IR-activities. This universality is then exploited by defining a new measure for evaluation in IR allowing for unbiased comparisons of all IR results. We also show that only using 1, 2 or even 3 measures from the set {P,R,F,M} necessary leads to evaluation measures that are nonuniversal and hence not capable of comparing different IR situations.