文本分类中一种新的特征选择方法

A new feature selection method in text categorization

在自动文本分类系统中,特征选择是有效降低文本向量维数的一种方法。在分析了常用的一些特征选择的评价函数的基础上,提出了一个新的评价函数,即互信息比值。实验证明这一方法简单可行,有助于提高所选特征子集的有效性。

Feature selection is a valid method to reduce the dimension of text vector in automatic text categorization system. After analyzing some normal evaluation functions for feature selection, a new evaluation function named the ratio of mutual information in feature selection was presented. Experiments show that the method is simple and feasible. It is advantageous in improving the efficiency of the selected feature subset.