EVALUATING RETRIEVAL PERFORMANCE GIVEN DATABASE AND QUERY CHARACTERISTICS - ANALYTIC DETERMINATION OF PERFORMANCE SURFACES

An analytic method of information retrieval and filtering evaluation c an quantitatively predict the expected number of documents examined in retrieving a relevant document. It also allows researchers and practi tioners to qualitatively understand how varying different estimates of query parameter values affects retrieval performance. The incorporati on of relevance feedback to increase our knowledge about the parameter s of relevant documents and the robustness of parameter estimates is m odeled. Single term and two term independence models, as well as a com plete term dependence model, are developed. An economic model of retri eval performance may be used to study the effects of database size and to provide analytic answers to questions comparing retrieval from sma ll and large databases, as well as questions about the number of terms in a query. Results are presented as a performance surface, a three d imensional graph showing the effects of two independent variables on p erformance.