Text Categorization Based on Naive Bayesian
Yaun Qi;Yu Qiao;Fujian Normal University;
Automatic text classification is an important application in the field of natural language processing by computer. Firstly, the paper mainly introduces the naive Bayesian classification theory.In this paper, we add measures to improve the performance of the basic Naive Bayesian classification method, including the calculation of mutual information of feature weight, Laplacian smoothing of zero probability, and an increase of computational stability by adding natural logarithm. This paper adopts Python programming language to design and achieves the naive Bayesian text classification experiment based on polynomial model, including the performance evaluation of text classification mode.
【CateGory Index】： TP391.1