基于特征选择的M-SVM中文文本分类  

Chinese Text Classification of M-SVM Based on Feature Selection

作　　者：刘永芬[1] 程丽 陈志安 LIU Yong-fen;CHENG Li;CHEN Zhi-an(Jinshan College of Fujian Agricultural and Forestry University,Fuzhou Fujian 350002;China Mobile Communication Group Company Limited Fujian Branch,Fuzhou Fujian 350001)

机构地区：[1]福建农林大学金山学院,福建福州350002 [2]中国移动通信集团福建有限公司,福建福州350001

出　　处：《软件》2019年第9期71-74,共4页Software

基　　金：福建省中青年教师教育科研项目,项目编号:JAT170894

摘　　要：在文本分类领域,中文文本需要经过数据处理,将文档表达成计算机可以理解并处理的信息。本文采用TF-IDF作为文本表示方法,针对中文文章的多分类问题,对传统支持向量机进行改进,提出了一种基于特征选择的多类支持向量机分类方法。在中文文章数据集的对比实验结果表明,本文的方法在多分类性能上较优于其他模式识别方法。In the field of text classification,Chinese text needs to be processed through data processing,and the document can be reached into information that can be understood and processed by computer.In this paper,TF-IDF is used as the text representation method to improve the traditional support vector machine(SVM)for the multi-classification problem of Chinese articles,and a multi-class support vector machine classification method based on feature selection is proposed.The experimental results show that the proposed method is superior to other pattern recognition methods in multi-classification performance.

关 键 词：M-SVM 特征选择 中文文本分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]