This session provides an overview of text analysis methods that are useful in humanities scholarship.  Participants will learn about the kinds of textual analysis that are possible using various techniques and concepts, including collocates, measures of distinctiveness and similarity (e.g., term frequency-inverse document frequency), collocates, topic modeling, and document classification. Using Voyant Tools for hands-on exploration, participants will learn how to apply these techniques to sample corpora and to their own research questions.  

Learning Outcomes: Participants will learn how to undertake some basic types of automated textual analysis using, e.g., metrics of document similarity.  Sample projects and suggested readings will illustrate the range of approaches, help to illustrate the affordances and limitations of each, and suggest the domains of relevant research questions.