Export Reviews, Discussions, Author Feedback and Meta-Reviews

The running application in this paper is the important problem of recommending scientific articles to people based on previous rating/interaction data. CTPF draws mainly upon two recent models: collaborative topic regression (CTR) of Wang and Blei and Poisson factorization of Gopalan et al. Each document is represented by two latent vectors in K-dimensional topic space: \theta, based on the text of the document, and \epsilon, based on the document's readers. Each user is represented by a latent K-dimensional topic affinity vector, x. Observed word counts for each document are drawn from a Poisson centered on the product of theta and the topic-word matrix, while the observed user-document ratings are drawn from a Poisson centered on x * (\theta + \epsilon), leading to a very elegant combination of text data and readership data. Authors present both batch and stochastic variational inference algorithms for approximating the posterior, and then experimental results showing state-of-the-art recall and precision @20 performance on two real-world data sets.