Abstract: World Wide Web is the store house of abundant information available in various electronic forms. Since past few years, the increase in the performance of computers in handling large quantity of text data has led researchers to focus on reliable and optimal retrieval of visible and implied information that exist in the huge resources. In text mining, one of the challenging and growing importance’s is given to the task of document classification or text characterization. In this process, reliable text extraction, robust methodologies and efficient algorithms such as Naive Bayes and other made the task of document classification to perform consistently well. Classifying text documents using Bayesian classifiers are among the most successful known algorithms for machine learning. This paper describes implementations of Naïve Bayesian (NB) approach for the automatic classification of Documents restricted to Technical Research documents based on their text contents and its results analysis. We also discuss a comparative analysis of Weighted Bayesian classifier approach with the Naive Bayes classifier.

Keywords: Classification; Naive Bayes; Weighted Bayesian.