Adaptive relevance feedback method of extended Boolean model using hierarchical clustering techniques Jongpill Choi a, * , Minkoo Kim a , Vijay V. Raghavan b a Department of Computer Engineering, Ajou University, Suwon, 443-749, Republic of Korea b The Center for Advanced Computer Studies, University of Louisiana, Lafayette, LA 70504, USA Received 21 June 2004; accepted 23 May 2005 Available online 19 July 2005 Abstract The relevance feedback process uses information obtained from a user about a set of initially retrieved documents to improve subsequent search formulations and retrieval performance. In extended Boolean models, the relevance feed- back implies not only that new query terms must be identified and re-weighted, but also that the terms must be con- nected with Boolean And/Or operators properly. Salton et al. proposed a relevance feedback method, called DNF (disjunctive normal form) method, for a well established extended Boolean model. However, this method mainly focuses on generating Boolean queries but does not concern about re-weighting query terms. Also, this method has some problems in generating reformulated Boolean queries. In this study, we investigate the problems of the DNF method and propose a relevance feedback method using hierarchical clustering techniques to solve those problems. We also propose a neural network model in which the term weights used in extended Boolean queries can be adjusted by the usersÕ relevance feedbacks. Ó 2005 Published by Elsevier Ltd. Keywords: Relevance feedback; Extended Boolean model; Hierarchical clustering; Multi-layer perceptron 1. Introduction Many relevance feedback methods have been studied (Ide, 1971; Rocchio, 1971; Salton & Buckley, 1990). The main idea of relevance feedback is to improve the retrieval performance by reformulating the queries based on usersÕ judgments of relevance of the retrieved documents. They are mostly based on the vector model for information retrieval. As an alternative to the conventional Boolean model, the vector 0306-4573/$ - see front matter Ó 2005 Published by Elsevier Ltd. doi:10.1016/j.ipm.2005.05.009 * Corresponding author. E-mail addresses: cjp@ajou.ac.kr (J. Choi), minkoo@ajou.ac.kr (M. Kim), raghavan@cacs.louisiana.edu (V.V. Raghavan). Information Processing and Management 42 (2006) 331–349 www.elsevier.com/locate/infoproman