A high performance algorithm for text feature automatic selection based on cloud model

Feature selection (FS) is one of the most important issues in text categorization (TC). At present, many effective FS methods have been put forward. For the purpose of acquiring the optimal number of features, these methods mainly depend on observation or experience. In this paper, a high performance algorithm for feature automation selection (FAS) is proposed. By using FAS, the feature set can be obtained automatically without any experience knowledge. Besides, it can effectively amend the distribution of features by using cloud model theory. Compared with the existing methods, FAS has fewer features and better classification performance. Accordingly, the corresponding time of TC has greatly decreased. Analysis and open experimental results fully prove it. 1553-9105/ Copyright © 2009 Binary Information Press.