Skip to Main Content

Digital Humanities: Text Analysis

This guide provides resources for faculty and students working on digital humanities research involving text analysis/text mining.

List of Tools

Voyant provides over 20 different tools you can use to analyze your text(s). This page will cover some popular ones, however, the full list can be accessed below.

Bubblelines

Cirrus

Contexts

Phrases

Summary

Terms


Note: Using the Document Terms tool in conjunction with the Documents tool will allow you see word counts for a specific document.

Trends


Note: In settings you can change "relative frequencies" to "raw frequencies" which will give an exact word count of the term per document.

Tools Usages

Below is a list of various text analysis activities and the corresponding tool(s) that can be used.

Text Analysis Activity Tool
Word count Terms; Document Terms
Create a word cloud Cirrus
Compare the frequency of terms across multiple documents/sections Trends
Determine document length Summary
Determine vocabulary density of a document (# of unique words/# of words) Summary
Average word count per sentence Summary
Determine words distinctive to a specific document in the context of a full corpus Summary
View word usage in varying contexts Contexts
Determine the most used phrases in a document/corpus Phrases
Visual representation of term frequency/repetition in a corpus Bubblelines

This list will be updated as additional popular text analysis activities are identified.