节点文献
文本分类中特征降维方式的研究
A Study on Feature Dimension Reduction in Text Categorization
【摘要】 首先介绍了几种常见的特征选择和特征抽取方法,并结合K-近邻分类算法对4种特征选择方法进行了分类测试,同时通过测试分析,提出了一些改进的、可行的互信息评价函数.
【Abstract】 This paper first introduces five methods of feature selection and feature extraction.Second,K-nearest neighbor is selected as an evaluating classifier to compare the performance of the four feature selection methods in TC.From the test result,a new improved method of FS is presented based on mutual information.The experiment results show that it is effective.
【关键词】 文本分类;
特征降维;
特征选择;
互信息;
【Key words】 text categorization; feature reduction; features selection mutual information;
【Key words】 text categorization; feature reduction; features selection mutual information;
- 【文献出处】 海南大学学报(自然科学版) ,Natural Science Journal of Hainan University , 编辑部邮箱 ,2007年01期
- 【分类号】TP391.1
- 【被引频次】20
- 【下载频次】314