I've been studying the Latent Dirichlet Allocation model this summer, and the literature can be very confusing for those without a rigorous background in Bayesian statistics. This paper provides a great intro to Bayesian Networks and Bayesian inference in general. It also gives a very clear explanation of topic modelling and derives a Gibbs Sampler for LDA inference.<p>I realize this post is kind of random, but I thought I'd pass this paper along in case others here are interested. It would have saved me alot of time if I had come across it four weeks ago.