Topic Modeling Tool

A graphical user interface tool for Latent Dirichlet Allocation topic modeling.

Purpose

This tool is for people who want to do their own topic modeling.

Topic Modeling

The topic model learns topics in a collection of documents, and tags each documents with a small number of topics.

#summary One-sentence summary of this page.

1. Download the software from here

2. Double-click the downloaded file to run it. If double-clicking does not run the application, you may need to install Java on your machine.

3. Select and download a testdata file from here. Use this text file as input to the system.

4. Set number of topics and the directory to which all output files are written.

You may also change more advanced options by clicking the Advanced button.

5. Click Train Topics to import the data and run the topic modeling algorithm. Depending on the size of the test collection, this may take several minutes.

6. Once complete, in a web browser, open up file all_topics.html under the output_html folder of the output directory to see the set of topics discovered. Click through the links to navigate between topics and documents.

7. Output results are also available as CSV files under the output_csv folder of the output directory.