Data Dialogue

Apr 14

Thursday, April 14, 2016

11:45 am - 12:45 pm
Gross Hall 330


Dr. Chris Bail, Duke University

Abstract: Social media sites are rapidly becoming one of the most important forums for public deliberation about advocacy issues. Yet social scientists have not yet explained why some advocacy organizations produce social media messages that inspire far ranging conversation among social media users, while the vast majority of them receive little or no attention. I combine network analysis and natural language processing to identify how the clustering of substantive topics within public conversations about Autism Spectrum Disorders enables and constrains advocacy organizations as they attempt to shape public discourse about this issue. I created a Facebook application that offered these organizations a complimentary audit of their social media strategy in return for sharing public and non-public data about their organization, its audience, and the broader social context in which they interact. Using time series models, I identify "ideal positions" within discursive networks that stimulate public conversation. I thereby contribute a novel theory of "cultural framing", new network-based techniques for automated text analysis, and describe the promise of social media applications for social science research.