Tidiers for Structural Topic Models from the stm package

Tidy topic models fit by the stm package. The arguments and return values are similar to lda_tidiers.

# S3 method for STM
tidy(x, matrix = c("beta", "gamma", "theta"), log = FALSE,
  document_names = NULL, ...)

# S3 method for STM
augment(x, data, ...)

# S3 method for STM
glance(x, ...)

Arguments

x	An STM fitted model object, created by stm.
matrix	Whether to tidy the beta (per-term-per-topic, default) or gamma/theta (per-document-per-topic) matrix. The stm package calls this the theta matrix, but other topic modeling packages call this gamma.
log	Whether beta/gamma/theta should be on a log scale, default FALSE
document_names	Optional vector of document names for use with per-document-per-topic tidying
...	Extra arguments, not used
data	For augment, the data given to the stm function, either as a dfm or as a tidied table with "document" and "term" columns

Value

tidy returns a tidied version of either the beta or gamma matrix. augment must be provided a data argument, either a dfm or a table containing one row per original document-term pair, such as is returned by tdm_tidiers, containing columns document and term. It returns that same data as a table with an additional column .topic with the topic assignment for that document-term combination. glance always returns a one-row table, with columns

k

Number of topics in the model

docs

Number of documents in the model

terms

Number of terms in the model

iter

Number of iterations used

alpha

If an LDA model, the parameter of the Dirichlet distribution for topics over documents

See also

lda_tidiers, stm

If matrix == "beta" (default), returns a table with one row per topic and term, with columns

topic

Topic, as an integer

term

Term

beta

Probability of a term generated from a topic according to the structural topic model

If matrix == "gamma", returns a table with one row per topic and document, with columns

topic

Topic, as an integer

document

Document name (if given in vector of document_names) or ID as an integer

gamma

Probability of topic given document

Examples

# NOT RUN {
if (requireNamespace("stm", quietly = TRUE) && requireNamespace("quanteda", quietly = TRUE)) {
  library(dplyr)
  library(ggplot2)
  library(stm)
  library(quanteda)

  inaug <- dfm(data_corpus_inaugural, remove = stopwords("english"), remove_punct = TRUE)
  topic_model <- stm(inaug, K = 3, verbose = FALSE, init.type = "Spectral")

  # tidy the word-topic combinations
  td_beta <- tidy(topic_model)
  td_beta

  # Examine the three topics
  td_beta %>%
    group_by(topic) %>%
    top_n(10, beta) %>%
    ungroup() %>%
    ggplot(aes(term, beta)) +
    geom_col() +
    facet_wrap(~ topic, scales = "free") +
    coord_flip()

  # tidy the document-topic combinations, with optional document names
  td_gamma <- tidy(topic_model, matrix = "gamma",
                   document_names = rownames(inaug))
  td_gamma

  # find the assignments of each word in each document
  assignments <- augment(topic_model, inaug)
  assignments
}
# }