Humanities researchers are often not accustomed to treating their objects of study as “data,” rather focusing on texts, collections, or cultural objects as the base unit of their research. However, the rich variety of data analysis tools in common practice allows for an incredible opportunity for expanded research avenues when humanities sources are treated as sources for data extraction.

This 90-minute, hands-on workshop will introduce Penn students to the ways humanities scholars of all levels can create, analyze, decode, and visualize data drawn from humanities sources. Participants will explore what it means to treat texts, places, and cultural artifacts as data, considering both the possibilities and limitations of computational approaches in humanities research. The session will provide an introduction to several tools for rapid data analysis including some AI-assisted coding approaches, while underscoring how humanists already work with data in everyday research in critical, ethical, and responsible ways.

Workshop attendees will introduced to basic text analysis concepts on humanistic corpora using Voyant, allowing participants to explore patterns across literary works, archival materials, and other textual data. Then students will be exposed to parsing more complex analytical methods through Python for tasks such as topic modeling and stylometry. No prior experience is required.