Elihu Katz Colloquium: Bryce Dietrich, University of Iowa  

Assessing Attitude Strength Using the Audio and Video from Telephone, In-Person, and Online Surveys
Bryce Dietrich
30 Oct 2020 - 12:00pm to 1:30pm
Virtual Event
Open to the Public

Share Facebook Twitter

This event will be held on Zoom. The link to join will be emailed to the Annenberg community on the day of the event.

About the Talk

Since Converse (1964), researchers have worked to distinguish between political attitudes which are consequential for political behavior and those that are not. This has motivated scholars to ask not whether attitudes predict behavior, but which attitudes predict behavior? Unfortunately, much of the information needed to answer this question is lost by the way survey responses are quantified, meaning what researchers often analyze are rough approximations of fully articulated opinions. Using a multi-input neural network and the audio and video from three different surveys, this study not only effectively measures attitude strength from open-ended responses, but when this is done — new insights are gained regarding when and where strong attitudes are articulated. Simply put, by not differentiating between different levels of attitude strength, researchers wrongly assume all responses are of equal quality. The measure introduced in this study not only avoids making such an assumption, but it is also embedded within software which will improve the quality of survey research by allowing scholars to automatically quantifying real-time audio streams.

About the Speaker

Bryce J. Dietrich is an Assistant Professor of Social Science Informatics in the Department of Political Science at the University of Iowa and the Iowa Informatics Initiative (UI3). His research uses novel quantitative, automated, and machine learning methods to analyze non-traditional data sources such as audio (or speech) data and video data. He uses these to understand the causes and consequences of elite emotional expression in a variety of institutional settings, with a particular emphasis on non-verbal cues, such as vocal pitch. More recently, he has used text, audio, and video analysis to explore issues related to descriptive representation and implicit gender/racial bias. His work has appeared in the American Political Science Review, Political Analysis, Political Psychology, and the Journal of Elections, Public Opinion, & Parties. He received his Ph.D. from the University of Illinois. He also received an MA from the University of Kansas. His work has received grant support from the NIH, Amazon, C-SPAN, and the Kinder Institute on Constitutional Democracy. It has also won the Kathleen L. Burkholder Prize from the University of Illinois and been featured in numerous popular outlets like BBC Radio, NPR, The Economist, the Washington Post, and FiveThirtyEight.

This event may be photographed and/or video recorded for archival, educational, and related promotional purposes. We also video stream many of these video recordings through the Annenberg web site. By attending or participating in this event, you are giving your consent to be photographed and/or video recorded and you are waiving any and all claims regarding the use of your image by the Annenberg School for Communication. The Annenberg School for Communication, at its discretion, may provide a copy of the photos/footage upon written request.