Divergence-Based Feature Selection for Na(i)e Bayes Text Classification

摘要：

A new divergence-based approach to feature selection for na?ve Bayes text classification is proposed in this paper. In this approach, the discrimination power of each feature is directly used for ranking various features through a criterion named overall-divergence, which is based on the divergence measures evaluated between various class density function pairs. Compared with other state-of-the-art algorithms (e.g. IG and CHI), the proposed approach shows more discrimination power for classifying confusing classes, and achieves better or comparable performance on evaluation data sets.

关键词： Divergence-based feature selection text classification overall-divergence

作者: Huizhen Wang Jingbo Zhu Keh-Yih Su

作者单位: Natural Language Processing Laboratory,Northeastern University,Shenyang,Liaoning,China Behavior Design Corporation Hsinchu,TAIWAN,R.O.C.

会议类型: 国际会议

会议名称: The 2008 IEEE International Conference on Natural Language Processing and Knowledge Engineering(IEEE NLP-KE 2008)(2008IEEE自然语言处理与知识工程国际会议)

会议地点: 北京

会议语种:英文

在线出版日期: 2008-10-19（万方平台首次上网日期，不代表论文的发表时间）