A Model for Evaluation of Interactive Information Retrieval
Nicholas J. Belkin, Michael Cole, Jun Liu · 2009
1.INTRODUCTION Research in information retrieval (IR) has expanded to take a broader perspective of the information seeking process to explicitly include users, tasks, and contexts in a dynamic setting rather than treating information search as static or as a sequence of unrelated events. The traditional Cranfield/TREC IR system evaluation paradigm, using document relevance as a criterion, and evaluating single search results, is not appropriate for many circumstances considered in current research. Several alternatives to relevance have been proposed, including utility, and satisfaction. We suggest an evaluation model and methodology grounded in the nature of information seeking and centered on usefulness. We believe this model has broad applicability in current IR research.