Michelle Torres - Give me the full picture: Using computer vision to understand visual frames and political communication

Date
-
Event Sponsor
The Munro Lectureship Fund
Location
Encina Hall West, Room 400 (GSL)
Speaker

Michelle Torres, Ph.D. Candidate in Political Science, Washington University in St. Louis

 

Abstract

Political communication is a central element of several political dynamics. Its visual component is crucial in understanding the origin, characteristics and consequences of the messages sent between political figures, media and citizens. However, visual features have been largely overlooked in Political Science. Thus, this article introduces a tool to dissect the structure and content of visual material in order to assess its relationship with political variables: the Bag of Visual Words (BoVW). The article details and validates the implementation of this intuitive and accessible technique for the extraction and quantification of visual features that allows researchers to build an Image-Visual Word matrix that emulates the Document-Term matrix in text analysis. Further, I illustrate its applicability by focusing on the identification of visual frames using a visual structural topic model. More specifically, I study the different depictions of certain political events and movements, like the migrant caravan and the Black Lives Matter movement, and find that the ideology of news outlets is associated with the generation of such visual frames.

 

Biography

Michelle Torres is an incoming Assistant Professor in the Department of Political Science at Rice University (starting July 2019). She holds a Ph.D. in Political Science and a A.M. in Statistics from Washington University in St. Louis. She is originally from Mexico City, where she obtained a B.A. in Political Science and International Relations from CIDE (Center for Research and Teaching in Economics). Her broad research interests are in the fields of political methodology and political behavior, with a special interest in survey methodology, computer vision, causal inference, public opinion, and political communication.