Topic Modeling for Humanities Research was a unique opportunity for cross-fertilization, information exchange, and collaboration between and among humanities scholars and researchers in natural language processing on the subject of topic modeling applications and methods. The workshop was organized into three primary areas:
- an overview of how topic modeling is currently being used in the humanities;
- an inventory of topic modeling methods that have particular relevance for humanities research questions; and
- a discussion of software implementations, toolkits, and applications.
The workshop was designed to foster collaboration between these communities by providing humanities scholars with a deeper understanding of latent variable modeling methods (and best practices for their interpretation), and by articulating fundamental literary and historical questions for researchers outside of the humanities who are developing the models and methods. The organizers encouraged applications from faculty, staff, and graduate students, as well as other academics and members of the general public with a serious interest in natural language processing, topic modeling, and the literary and historical questions that intersect with these research areas. Confirmed speakers include: Matthew Jockers of the University of Nebraska, David Mimno of Princeton University, Rob Nelson of the University of Richmond, Jordan Boyd-Graber of the University of Maryland, and more.