Tracking Collective Response to Terrorist Attacks Using Social Media Sensors
Date: October 24, 2016
Time: 12:00pm – 1:00pm
Room: Wells Library, Rm LI 001
Terrorism aims to provoke adverse psychological outcomes, which can have both immediate and long-term negative impact on its targeted communities. Developing ways to effectively assess and mitigate such impact requires a better understanding of how the communities experienced and coped with the terrorist incidences. However, it is difficult to study these mechanisms with traditional social science methodologies such as laboratory experiments and longitudinal survey panels. In this talk, I will introduce a complementary methodology, termed “computational focus groups,” that utilizes data collected from social media streams to analyze the dynamics of collective response following disaster events. I will present a series of studies that systematically examine the emotional response and behavioral changes after major terrorist events, including the 2013 Boston Marathon bombings and the 2015 Paris attacks. Our study of the Boston Marathon bombing event showed how a disruptive event triggered inter-communal emotions and expressions — where members of one community expressed feelings about and support for members of a distant community. The analyses of the Paris and Brussels attacks indicated that, while proximity, gender, and social interaction have measurable impacts on these emotional reactions, news media exposure had competing, time-dependent effects on anxiety. These results have theoretical implications regarding the diffusion of information and emotional contagion as well as practical implications for understanding how important information and social support can be effectively collected and distributed to populations in need.
Yu-Ru Lin is an assistant professor at the School of Information Sciences, University of Pittsburgh. She received the PhD degree in computer science with a concentration in Arts, Media and Engineering from Arizona State University. Her research interests include human mobility, social and political network dynamics, and computational social science. She has developed computational approaches for mining and visualizing large-scale, time-varying, heterogeneous, multi-relational, and semi-structured data. Her current research focuses on tracking and modeling collective behavior from big data sets, including social media data and anonymized cellphone records, for understanding human and social dynamics, particularly under exogenous events such as emergencies and media events. Her work has appeared in prestigious scientific venues including WWW, SIGKDD, SIGCHI, AAAI, InfoVis, ACM TKDD, ACM TOMCCAP, IEEEP, PLoS ONE, and Data Science. Her research vision is to use big data in the service of humanity, through developing new methodologies to collect, mine and utilize information to support collective sensemaking. Additional information can be found at: http://www.yurulin.com.