Bayesian Text Classification and Summarization via A Class-Specified Topic Model

We propose the class-specified topic model (CSTM) to deal with the tasks of text classification and class-specific text summarization. The model assumes that in addition to a set of latent topics that are shared across classes, there is a set of class-specific latent topics for each class. Each document is a probabilistic mixture of the class-specific topics associated with its class and the shared topics. Each class-specific or shared topic has its own probability distribution over a given dictionary. We develop a Bayesian inference of CSTM in the semisupervised scenario, with the supervised scenario as a special case. We analyze in detail the 20 Newsgroups dataset, a benchmark dataset for text classification, and demonstrate that CSTM has better performance than a two stage approach based on latent Dirichlet allocation (LDA), several existing supervised extensions of LDA, and an $L^1$ penalized logistic regression. The favorable performance of CSTM is also demonstrated through Monte Carlo simulations and an analysis of the Reuters dataset. [abs] [ pdf ][ bib ] © JMLR 2021. (edit, beta)