Topic modeling is a text mining method that uses algorithms to discover hidden patterns and structures in large collections of texts. A topic modeling program extracts abstract “topics” by identifying and grouping words that frequently co-occur in a text. This workshop will introduce topic modeling with MALLET, a Java-based package for statistical natural language processing, topic modeling, and other machine learning applications to text. Participants will learn how to create and interpret topic models using MALLET.

Workshop preparation: Participants should install MALLET before joining the workshop. For installation instructions, see Getting Started with Topic Modeling and MALLET: Installing MALLET.

This workshop is part of our Digital Humanities Toolkit Series.

Please check in with the presenter for your workshop or contact Gesina Phillips (gap64@pitt.edu) if you have any pre-event questions. If you are not a Pitt affiliate, most software should still be available to you, with the exception of ArcGIS and Photoshop--please get in touch if you have any other questions about your ability to participate.