The improved features selection for text classification

With the development of modern social technology and people´s constant pursuit for knowledge, a more diverse and open cyber space is becoming the fact in academic field. In this environment, it is more necessary than ever before that people extract comprehensive, efficient, and valuable information from a wide range of cultural information. Therefore, text categorization research has become more important. The paper improved the precision of the traditional text categorization by the process that we mended the weight of words and mined potential keywords, then found their relationship. In the end of the paper, an experiment was used to illustrate the process of features extraction.