Text Analysis

Text analysis is the computational process of identifying patterns and trends across a large body of natural language documents or documents composed of human language. This process is often referred to as "distant reading," and uses a technique called machine learning to organize and describe the documents on the whole, individually, or by groupings. Text analysis can complement traditional close readings of texts as it provides insights into word usage, word associations, underlying tendencies and biases, etc. that may go unnoticed without the assistance of computational methods.

This guide provides an introduction to the different phases of a text analysis project and offers resources to accomplish each stage.

The following is a selection of digital projects utilizing various methods of text analysis. These projects can provide an insight into how text analysis can diversify your scholarship and provide new insights into your sources.

America's Public Bible - Lincoln Mullen

Mining the Dispatch - Robert K. Nelson

"Everything on paper will be used against me": Quantifying Kissinger - Micki Kaufman

Topic Modeling Martha Ballard's Diary - Cameron Blevins

Viral Texts - Ryan Cordell and David Smith

Signs@40 - Andrew Mazzaschi, Mary Hawkesworth, Andrew Goldstone, Susana Galán, C. Laura Lovin, Lindsey Whitmore, Miranda Outman

Please see the following related libguides for additional help in your digital scholarship projects:

Digital Humanities: Learn about the digital humanities production taking place here and learn about BSU's involvement in the Indiana Digital Humanities Initiative.

Data Management & Sharing: Find resources and direction for planning and drafting data management plans.

Omeka: A guide to Omeka, a web publishing platform for online archives, collections, and exhibits.