基于SVM与KNN的中文文本分类比较实证研究

Empirical Study of the Comparison of SVM and KNN-based Categorization of Chinese Text

本文详细介绍了中文文本分类过程以及SVM和KNN两种方法在中文文本分类中的具体步骤,给出了中文文本分类的模型。通过实验对SVM算法和传统的KNN算法应用于文本分类效果进行了比较性实证研究。研究表明,SVM分类器较KNN在处理中文文本分类问题上有更良好的分类效果,有较高的查全率和查准率。

After describing the categorization process of the Chinese text and the concrete steps of using SVM and KNN to categorize the Chinese text,a model of Chinese text categorization is proposed.An empirical study of using the SVM algorithm and the traditional KNN algorithm to categorize the Chinese text is conducted.The experiment shows that,compared with KNN,SVM has better categorization effect of the Chinese text and higher recall ratio and pertinency ratio.