Using Fuzzy LR Numbers in Bayesian Text Classifier for Classifying Persian Text Documents

Abstract

Text Classification is an important research field in information retrieval and text mining. The main task in text classification is to assign text documents in predefined categories based on documents' contents and labeled-training samples. Since word detection is a difficult and time consuming task in Persian language, Bayesian text classifier is an appropriate approach to deal with different word formats and new words. Also, fuzzy theory may be used to manage uncertainty in imprecise Persian sentences. In this paper, we utilize L-R type fuzzy numbers in Bayesian text classifier to classify textual Persian documents (Fuzzy Bayesian text classifier). The obtained results on simulated imprecise textual Persian documents show improvements in both recall and precision parameters by using Fuzzy Bayesian text classification approach over Naïve Bayesian text classifier