Abstract Supervised topic models leverage label information to learn discriminative latent topic representations. As collecting a fully labeled dataset is often time-consuming, semi-supervised learning is of high interest. In this paper, we present an effective semi-supervised max-margin topic model by naturally introducing manifold posterior regularization to a regularized Bayesian topic model, named LapMedLDA. The model jointly learns latent topics and a related classififier with only a small fraction of labeled documents. To perform the approximate inference, we derive an effificient stochastic gradient MCMC method. Unlike the previous semi-supervised topic models, our model adopts a tight coupling between the generative topic model and the discriminative classififier. Extensive experiments demonstrate that such tight coupling brings signifificant benefifits in quantitative and qualitative performance