Using clustering and classification approaches in interactive retrieval

Satisfying non-trivial information needs involves collecting information fr om multiple resources, and synthesizing an answer that organizes that infor mation. Traditional recall/precision-oriented information retrieval focuses on just one phase of that process: how to efficiently and effectively iden tify documents likely to be relevant to a specific, focused query, The TREC Interactive Track has as its goal the location of documents that pertain t o different instances of a query topic, with no reward for duplicated cover age of topic instances. This task is similar to the task of organizing answ er components into a complete answer. Clustering and classification are two mechanisms for organizing documents into groups. In this paper, we present an ongoing series of experiments that test the feasibility and effectivene ss of using clustering and classification as an aid to instance retrieval a nd, ultimately, answer construction. Our results show that users prefer suc h structured presentations of candidate result set to a list-based approach . Assessment of the structured organizations based on the subjective judgem ent of the experiment subjects suggests that the structured organization ca n be more effective; however, assessment based on objective judgements show s mixed results. These results indicate that a full determination of the su ccess of the approach depends on assessing the quality of the final answers generated by users, rather than on performance during the intermediate sta ges of answer construction. (C) 2001 Elsevier Science Ltd. All rights reser ved.