Co-EM Support Vector Machine Based Text Classification from Positive and Unlabeled Examples

摘要：

This paper has brought about a novel method based on multi-view algorithms for learning from positive and unlabeled examples(LPU).First we,with an improved 1-DNF method,split the text feature into a positive feature set(PF)and a negative feature set(NF).And we project each text vector on the two feature sets in turn.Then we use the co-EM SVM algorithm,which was previously used for semisupervised learning.Finally,we select the better classifier for the result.Comprehensive evaluation has been performed on the Reuers-21578 collection which shows that our method is efficient and effective.

作者: ZHANG Bang-zuo ZUO Wan-li

作者单位: College of Computer Science and Technology,Jilin University,Changchun,China,130012;College of Comput College of Computer Science and Technology,Jilin University,Changchun,China,130012

会议类型: 国际会议

会议名称: 第一届智能网络与智能系统国际会议(ICINIS 2008)(The First International Conference on Intelligent Networks and Intelligent Systems)

会议地点: 武汉

会议语种:英文

在线出版日期: 2008-11-01（万方平台首次上网日期，不代表论文的发表时间）