“Topic modeling” is a text mining process that uses word co-occurrences to help discover hidden patterns in large collections of texts. This workshop will introduce topic modeling with MALLET, a Java-based software tool for statistical natural language processing. Participants will learn how to create and interpret topic models using MALLET, a common workflow in the Digital Humanities.

This workshop is also part of Processing Community Day @ Pittsburgh, a national day with local activities. The instructors provide a space for people to learn how to program and make creative work with code, reaching out to diverse communities, especially those who might not otherwise have access to these tools and resources.

Level: Intermediate (participants should have some modest prior scripting or programming experience).

Equipment: Computers provided.