关键词: 文本分类, 朴素贝叶斯方法, k-最近邻方法（kNN）, 维吾尔语, 特征选择

Abstract: With the rapid increase of Uyghur language text information on the Internet, Uyghur language text categorization has become a key technique for processing and organizing these text data. As to the high dimensionality of Uyghur language texts under vector space model representation, the stemming technique is used along with IG to reduce the dimensionality. The categorization experiments are performed using machine learning based text categorization algorithms such as Na?ve Bayes and kNN on Uyghur language text corpus and the experimental results are analyzed.

Key words: text categorization, Na?ve Bayes, k-Nearest Neighbor（kNN）, Uyghur language, feature selection