【摘要】 在文本分类系统中,特征选择方法是一种有效的降维方法。在分析了几种常用的特征选择评价函数之后,将权值计算函数应用于特征选择,并基于改进的TFIDF方法提出了一种新的评价函数,它将类别信息引入到特征项中,提取出与类别相关的特征项,弥补了TFIDF的缺陷。实验证明该方法简单可行,有助于提高所选特征子集的有效性。更多还原

【Abstract】 Feature selection is a valid method to reduce the dimension of vector in text categorization system. After analyzed several common evaluation functions for feature selection, terms weight function is applied in feature selection, A new evaluation function based on improved TFIDF method is presented. The category information is introduced to feature items in this new method. The feature items of relevant categories are selected to make up the shortcomings of the TFIDF. Experiments proved that the method is simple and feasible. It’s advantageous in imoroving the efficiency of the selected feature subset.更多还原