基于优化的文档频和粗糙集的特征选择方法

Feature Selection Method Based on Optimized Document Frequency and Rough Sets

特征选择是文本分类的一个核心研究课题.首先给出了一个基于最小词频的文档频方法,然后把粗糙集引入进来并提出了一个属性约简算法,最后把该属性约简算法同基于最小词频的文档频方法结合起来,提出了一个综合的特征选择方法.该综合方法首先使用基于最小词频的文档频方法进行特征初选以过滤掉一些词条来降低特征空间的稀疏性,然后利用所提属性约简算法消除冗余,从而获得较具代表性的特征子集.

Feature selection is the core research topic in text categorization. Firstly, a document frequency method based on minimum word frequency is presented. And then, rough sets are introduced and an attribute reduction algorithm is provided. Finally, the attribute reduction algorithm is combined with the document frequency method based on minimum word frequency and a comprehensive feature selection method is proposed. The comprehensive method firstly uses the document frequency method based on minimum word frequency to select feature and filter out some terms to reduce the sparsity of feature spaces, and then employs the attribute reduction algorithm to eliminate redundancy, so that the feature subset which are more representative is acquired.