Topic Modeling is a text-mining method that allows the user to uncover thematic patterns in their Content Set by identifying ‘Topics’, or groups of commonly occurring terms.  

The Topic Modeling algorithm in Gale Digital Scholar Lab identifies words in the documents contained in a Content Set that are statistically more likely to occur near each other. When identified, these words are grouped into numbered topics that can then be labelled by the researcher. Users can interrogate, explore and classify these topics to further investigate documents, uncovering common themes and trends within their Content Set.  

Topic Modeling encourages deeper analysis of documents than is often possible through traditional reading. It provides a lens through which researchers can examine individual documents according to the ratio of each topic within them.  

Learn more about how to use Topic Modeling to classify and investigate documents here. 

PROJECTS

The Books He Carried: A Study of Lindsley Foote Hall's Reading Habits on His Travels | Julianne Peeling (University of Washington)  

Of Christ and Capital: The 'Sunday Question' in the 1893 Columbian Exposition | Marie Peeples, Ian Reinl, Elise Tomasian, Danielle Worthy (University of Washington)

A Digital Historiography of treaties and disputes between the coast Salish tribes and U.S. government | Marie Christine O'Connell (University of Washington)

Tracking Archaeology in The Illustrated London News

Sample Project 1: Black America and the Law in the Mid-20th Century

Sample Project 2: The Rise of Electricity in the Late 19th and Early 20th Centuries

Sample Project 3: Food and Civility 1650-1800