To identify the societal risk category of the posts of Tianya Club, several studies are carried out toward the posts of Tianya Club. With 2-month manually risk labeled new posts published during December of 2011 to January of 2012, statistical analysis of posts is conducted at first. Later, similarity analysis of posts from one risk category, different risk categories and published on different...

Recent studies disclose that maximizing the minimum margin like support vector machines does not necessarily lead to better generalization performances, and instead, it is crucial to optimize the margin distribution. Although it has been shown that for binary classification, characterizing the margin distribution by the firstand second-order statistics can achieve superior performance. It still...

We study supervised and semi-supervised algorithms in the set-valued classification framework with controlled expected size. While former methods can use only n labeled samples, latter are able to make of N additional unlabeled data. obtain minimax rates convergence under α-margin assumption a β-Hölder condition on conditional distribution labels. Our analysis implies that if no further is made...