Labeled LDA-Kernel SVM: A Short Chinese Text Supervised Classification Based on Sina Weibo

At present, it is a great challenge that solving high-dimension and text sparsity problems in short text classification. To resolve these problems, this paper proposes a method which takes the correlation between lexical items and tags before completing Latent Dirichlet Allocation(LDA) topic model. Meanwhile, this paper adjusts parameters of Support Vector Machine(SVM) to find the optimal values by K-fold cross validation. Besides, using kernel SVM as classifier, we successfully categorize labeled short Chinese text documents. Comparing with other two conventional methods k-Nearest Neighbor and Decision Tree of short text classification, the experimental results show that our method outperforms them on classification accuracy, precision, recall and F-measure.