Topwords

The topwords module provides tools for identifying prominent words and terms in a corpus.

Keyword Extraction

Algorithms for extracting key terms from documents are found in the keyterms sub-module.

Statistical Comparisons

Tools for comparing word frequencies across different parts of a corpus are found in:

• Compare: A base class for topword comparisons.
• Mann-Whitney U Test: Statistical comparison using the Mann-Whitney U test.
• Z-Test: Statistical comparison using a Z-test for proportions.