Order for Guest
Your shopping cart is empty.
Department of Psychology Presents

The Structural Topic Model: Text Analysis with Document Context by Brandon Stewart

3/24/17, 2:00 PM

About this event

Please join us on March 24, from 2:00 - 3:00 pm in N219 Elliott Hall (Department of Psychology) for the 5th annual Quantitative Methods Colloquium sponsored by the CLA Quantitative Methods Collaboration Committee.  This year our guest speaker is Professor Brandon Stewart from Princeton University.  Although Brandon is still a young professor (Harvard PHD, 2015), his work has already garnered a great deal of enthusiasm and interest in the fields of Political Science, Sociology, and Computational linguistics.  The title of Brandon’s talk is: The Structural Text Model: Text Analysis with Document Context. An abstract of his talk follows:

Statistical models of text have become increasingly popular in statistics and computer science as a method of exploring large document collections. Social scientists often want to move beyond exploration, to measurement and experimentation, and make inference about social and political processes that drive discourse and content. I provide an overview of the Structural Topic Model, a statistical model of text data that supports this type of substantive research.  The statistical methods are illustrated with a variety of examples from the social sciences. Software and papers are available at structuraltopicmodel.com

Persons interested in meeting Brandon should contact Niels Waller: nwaller@umn.edu
Event Location
  • Campus Club Coffman Memorial Union
  • USA