Text categorization with k-nearest neighbor approach

Abstract

World Wide Web is the store house of abundant information available in various electronic forms. In the past two decades, the increase in the performance of computers in handling large quantity of text data led researchers to focus on reliable and optimal retrieval of information already exist in the huge resources. Though the existing search engines, answering machines has succeeded in retrieving the data relative to the user query, the relevancy of the text data is not appreciable of the huge set. It is hence binding the range of resultant text data for a given user query with appreciable ranking to each document stand as a major challenge. In this paper, we propose a Query based k-Nearest Neighbor method to access relevant documents for a given query finding the most appropriate boundary to related documents available on web and rank the document on the basis of query rather than customary Content based classification. The experimental results will elucidate the categorization with reference to closeness of the given query to the document. © 2012 Springer-Verlag GmbH Berlin Heidelberg.