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

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 semi-supervised 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.