Application for Web Text Categorization Based on Support Vector Machine

This paper put forward a text categorization method based on Naive Bayes learning support vector machine. First adopt the text pre-processing. Then vector space model and linked list of technical are used to extract text features, reduce dimensions according to the characteristics of the text. Then after Naive Bayes algorithm been proposed to train the support vector machines, support vector machines is used to new text categorization. Then the experiment method and result are given. The results show that the method proposed are not only more reliable, but also further improve the precision classification comparing with traditional support vector machines algorithm.