Classification of Text Documents

Abstract

Nowadays, the text information is available in electronic form which is easily accessible to people, due to whom it is increasing day by day, but the challenging issue is to organize the information. The existing algorithm such as naïve Bayes classifier uses the maximum posterior estimation for building a classifier, but it is dependent on huge number of training samples for more accuracy and the other algorithm known as genetic algorithm that begins with an initial population which is constructed from randomly generated rules, but the accuracy of this algorithm depends on set of training examples. In this paper, we are using brute-force approach to classify the different categories of documents.