Calculate a topic model — run_topic_model • revtools

Calculate a topic model using Latent Dirichlet Allocation (LDA) or Correlated Topic Models (CTM), using the topicmodels package.

run_topic_model(dtm, type = "lda", n_topics = 5, iterations = 2000)

Arguments

dtm: a Document Term Matrix (DTM)
type: string specififying the type of model to run. Either 'lda' (the default) or 'ctm'.
n_topics: Number of topics to calculate
iterations: The number of iterations. Only relevant for LDA.

Value

A topic model with the specified parameters.

Note

This is a basic wrapper function designed to allow consistent specification of model parameters within shiny apps.

See also

make_dtm for constructing data to pass to this function; screen_topics for interactive visualisation of topic model results.

Examples

# import data
file_location <- system.file(
  "extdata",
  "avian_ecology_bibliography.ris",
  package = "revtools"
)
x <- read_bibliography(file_location)

# run a topic model based on these data
# note: the following lines can take a very long time to run, especially for large datasets!
x_dtm <- make_dtm(x$title)
if (FALSE) x_lda <- run_topic_model(x_dtm, "lda", 5, 5000)