kkdey/classtpx: MAP Estimation using topic models in a semi-supervised set up where there are few samples with known topic proportions or known to belong to some cluster exclusively and there are samples for which no such information are available.

Posterior maximization for semi-supervised topic models (LDA). The methods are as described in Taddy (2012) `on estimation and selection for topic models'. Previous versions of this code were included as part of the textir package. If you want to take advantage of openmp parallelization, uncomment the relevant flags in src/MAKEVARS before compiling.

install.packages("remotes")
remotes::install_github("kkdey/classtpx")