dfrtopics: Explore and analyze topic models

In agoldst/dfrtopics: Tools for exploring topic models of text

Explore and analyze topic models

Description

This package supplies functions for creating and analyzing topic models using MALLET. It has numerous functions to help process data from one particular source, JSTOR's Data for Research service, but the modeling and exploration functions are independent of that source. It uses mallet, the R wrapper for MALLET, for modeling. A detailed walkthrough of the package can be found in the "Introduction" vignette. A companion project, dfr-browser, uses JavaScript to create an interactive model browser in a web browser. To explore a model with dfr-browser, use the dfr_browser function. To save the model outputs produced in this package into files formatted as dfr-browser requires, use export_browser_data.

Examples

## Not run: 
# Please see vignette("introduction", "dfrtopics") for more examples
# But to play with a first model:
# Put a DfR download in "dfr-data" and run:
m <- model_dfr_documents(
    citations_file="dfr-data/citations.tsv",
    wordcounts_dirs="dfr-data/wordcounts",
    n_topics=20  # or any other initial topic guess
)
topic_labels(m)
plot_series(topic_series(m))
dfr_browser(m)

## End(Not run)

agoldst/dfrtopics documentation built on July 15, 2022, 4:13 p.m.