Streaming Live: https://www.youtube.com/user/citpprinceton

Food and discussion begin at 12:30pm. Open to current Princeton faculty, staff, and students. Open to members of the public by invitation only. Please contact Laura Cummings-Abdo at if you are interested in attending a particular lunch.

The use of social media data in combination with data from more traditional political science data-sources presents several scientific opportunities to study how individuals and groups make decisions about political participation. Every time individuals use social media, they leave behind a digital footprint of what was communicated, when it was communicated, and to whom it was communicated. Typically, such precise estimates of these variables are available only to laboratory investigators working in artificial settings, and thus integration of social media data into political science and social psychology studies of political behavior results in datasets that reveal preference, ideology, dynamics, location and social connectivity with unprecedented resolution and comprehension. In spite of these potential gains, the use of social media presents several technical challenges including: reproducibly storing and accessing these large data-sets, coding/classification of tweets and other social media content, and distinguishing active social links and active users from inactive. Our aim is to create an infrastructure that enables collaboration by removing the technical barriers for social scientists and the pedagogical barriers for computer scientist entering this field. In the first part of this presentation we will describe the infrastructure we have developed to integrate information on social network connectivity with metadata on individuals and their social contacts to enable multiple studies. We will then discuss several current SMaPP projects including: 1) using social media to estimate ideology and explore the differences in polarization for different topics (Superbowl, US elections, Boston bombing), 2) the evolution of the #Euromaidan protest in Ukraine, and 3) predicting individual level behaviors during the recent government shutdown. Lastly we will discuss unsolved problems including the current machine learning challenges presented by these projects.

Bios:

Rich Bonneau is an Associate Professor of Biology and Computer Science at NYU, the co-Director of the Social Media and Political Participation Lab at New York University and the Systems Biology group leader at the newly formed Simons Center for Data Analysis in New York. The focus of his computational biology work is on creating new methods for using protein structure modeling to interpret genetic variation and new methods for understanding biological networks. Previously Dr. Bonneau was a senior scientist at the Institute for Systems Biology in Seattle (the ISB at the time was the leading innovator in biotechnology and systems approaches to biological networks) and before that he was a senior scientist at Structural GenomiX in San Diego, California. Dr. Bonneau, through his participation in the NYU SMaPP, aims to ultimately compare the structure and dynamics of biological networks (that we have just recently figured out how to learn from genomics data) with social network models (that we are just beginning to build from multiple data sources including social media). See Dr. Bonneau’s work on Google Scholar. Follow him on Twitter @RichBonneauNYU

Joshua A. Tucker is a Professor of Politics and (by courtesy) Russian and Slavic Studies at New York University, a co-Director of the NYU Social Media and Political Participation (SMaPP) laboratory (smapp.nyu.edu), and a co-author of the award winning Monkey Cage blog at The Washington Post. He is also one the founding co-editors of the Journal of Experimental Political Science, the Vice-President of the Midwest Political Science Association, and serves on the Editorial Board of multiple academic journals as well the Advisory Board of the American National Election Study. Professor Tucker specializes in the study of mass political behavior, including elections and voting, the development of partisan attachment, public opinion formation, mass protest, and the relationship between social media and political participation. He is the author of Regional Economic Voting: Russia, Poland, Hungary, Slovakia, and the Czech Republic, 1990-99 (Cambridge University Press, 2006). His work has appeared in numerous academic journals, including the American Journal of Political Science, the British Journal of Political Science, Comparative Politics, Comparative Political Studies, the Journal of Politics, and the Annual Review of Political Science, and his opinions have been published in The New Republic, The Wall Street Journal, Al Jazeera English, Time, and the International Herald Tribune. In 2006, he was awarded the Emerging Scholar Award for the top scholar in the field of Elections, Public Opinion, and Voting Behavior within 10 years of the doctorate. In 2012 he was part of an interdisciplinary four-person team of NYU faculty to win one the National Science Foundation’s inaugural INSPIRE – CREATIV grants. Follow him on Twitter @j_a_tucker.