Abstract:

The automatic text categorization technique has important practical significance and broad application prospect in improving the validity and accuracy of the use of text information.With the rapid increase of Uyghur language text information on the Internet,Uyghur language text categorization has become a key technique of processing and organizing these text data.As to the high dimensionality of Uyghur language text under vector space model representation,the stemming technique is used along with χ2 to reduce the dimensionality.Uyghur language text categorizer is constructed based on SVM.The experimental results based on Uyghur language text corpus show that the MacroF1 value of SVM categorizer can reach 84.6% and outperform the kNN approach.

Key words: text categorization;SVM;kNN;uyghur language