Exploring Societal Risk Classification of the Posts of Tianya Club

摘要

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 days are implemented Finally, multi-class classification of posts using support vector machine (SVM) with different training set is tested. The statistical analysis and similarity analysis reveals the difficulties in multi-class classification of the posts of Tianya Club. The multi-class predictive results indicate that SVM could be applied to multi-class classification of posts, but still need further exploitation.