Study on feature selection in finance text categorization

Document genre information is one of the most distinguishing features in information retrieval, which brings order to the search results. What the genre classification concerned is not the topic but the genre of document. In this paper, two different feature sets were employed: bag of words which are derived by feature selection method and structural features which are selected manually and subjectively. And a comparative study on feature selection in genre classification of Chinese finance text is presented. In empirical results with classifiers on the real world corpora, we find that those manual labeled features can improve the performance clearly.