基于文本属性关联和概念共现的KNN分类方法  

An K-nearest Neighbor Classification Method Based on Text Attribute Association and Concept Cooccurring.

作　　者：程传鹏[1] 李钜[1] 

机构地区：[1]中原工学院,郑州450007

出　　处：《中原工学院学报》2009年第4期27-29,共3页Journal of Zhongyuan University of Technology

基　　金：河南省教育厅软科学项目(2008b520046)

摘　　要：介绍了基于向量空间模型(VSM)中的KNN文本分类方法,分析了KNN方法的实质,指出了该方法的不足,基于文本属性关联和概念共现对KNN分类中的文档相似性度量公式提出了改进.分类实验结果表明,分类准确率平均提高了10%.Based on the vector space model （VSM） in the KNN text classification methods,this paper first analysed the kNN＂ s physical meanings in the VSM and its weakness, then put forward an improved method, which is based on text attribute association and concept cooccurring. Results of experimental show that the accuracy ratio is improved by 10%.

关 键 词：文本分类 KNN 向量模型 相似度 

分 类 号：TP391.07[自动化与计算机技术—计算机应用技术]