One of the challenges facing social scientists is that our understanding of how social and political processes operate and what their consequences are has lost some of its predictive power, such as our failure to predict election outcomes. This phenomenon raises questions of whether theories and models developed in the past – among a different generation living in a different cultural and technological setting – apply in the current environment. Concurrently, the abundance of online, social media data provides the social scientists with great opportunities to understand today’s social and political phenomena. To use such opportunities, however, important issues on how to process and use social media need to be addressed. Such issues include whether social media users are representative of the population at large and whether they are honest and open, as well as whether the collection and processing of data are unbiased and accurate to allow the construction of inferences about populations.
The research team will carry out a few parallel projects with the unifying theme of integrating geospatial, social media and spatial data to address research and methodological questions. One project is about communication patterns and their effects on political choices and behavior in the 2016 presidential election. The second project investigates online and Twitter communication about parenting information and misinformation. A third project will investigate a variety of methodological issues associated with inferences drawn from probability-based and nonprobability-based social surveys and from social media. The three projects will employ methods of cross-validation of survey data, social media, and administrative records and investigate the social network dynamics of elites and the general public. The research team will develop procedures for extracting meaning from large collections of text to connect with public attitudes about important political and policy issues of the day. They will also develop visualization techniques for dimensionality reduction, while expanding upon existing systems for data mining and statistical inference.
The project is a collaboration between researchers from multiple units at the University of Michigan and at Georgetown University, and the team will also engage researchers at Gallup. This set of projects will become the locus for multidisciplinary efforts between social scientists, computer scientists, and statisticians at both institutions, and each university will become the locus for future extended work of this kind. The data science tools developed through this set of projects will also have wide application to other research questions in social science.
Michael Traugott, Principal Investigator, Research Professor, Institute for Social Research
Trivellore Ragunathan, Professor, Department of Biostatistics and Institute for Social Research
Leticia Bode, Associate Professor, Communication, Culture and Technology Program, Georgetown University
Ceren Budak, Assistant Professor, School of Information
Pamela Davis-Kean, Professor, Department of Psychology and Institute for Social Research
Jonathan Ladd, Associate Professor, McCourt School of Public Policy, Georgetown University
Zeina Mneimneh, Assistant Research Scientist, Institute for Social Research
Josh Pasek, Associate Professor, Department of Communication and Media
Rebecca Ryan, Associate Professor, Department of Psychology and McCourt School of Public Policy, Georgetown University
Lisa Singh, Associate Professor, Department of Computer Science and McCourt School of Public Policy, Georgetown University
Stuart Soroka, Professor, Department of Communication and Media and Department of Political Science
The book Words That Matter: How the News and Social Media Shaped the 2016 Presidential Campaign (Brookings Institution Press, 2020) is now available. A summary of the book’s key findings appear in a write-up on the Gallup website. Three of the book’s contributors discussed the book in an audio excerpt recorded for a book launch party at the 2020 annual meeting of the American Association for Public Research. A brief summary and cover of the book are provided here.
- Coverage on CNN: Read: The methodology behind new polling project The Breakthrough(August 16, 2020)
- The Political Communication group published a chapter “Attention to Campaign Events: Do Twitter and Self-Report Metrics Tell the Same Story?” in Big Data Meets Survey Science: A Collection of Innovative Methods (Wiley, 2020)
The S3MC team released a white paper “Data Blending: Haven’t We Been Doing This For Years?” (Massive Data Institute, Georgetown, 2020) that discussed traditional and new (i.e., data science) approaches to data blending.
The S3MC team was awarded a Convergence grant from NSF to continue developing their multidisciplinary and multimethodological work to advance our understanding of human behavior and society. For more information about this work, visit their website.
- The team has started a new project with CNN for the 2020 presidential election, and the first release is here.
- The Political Communication group is working on an edited volume about the 2016 campaign that will be published by Brookings. This involves developing new strategies for retrieval of news coverage of political events and analysis software.
- The Parenting Group is moving ahead with plans for coding a large amount of Twitter data, starting with human coding of samples of Tweets.
- The Survey Methodology Group has been designing a survey to capture information from Twitter users and nonusers in order to address issues of representativeness in data collected through social media.
The parenting group presented at the Society for Research in Child Development Biennial Conference. The parenting group has also submitted a proposal to the National Science Foundation on Resource Implementations for Data Intensive Research. The team also has a book under contract with Brookings (Words that Matter, How the News and Social Media Shaped the 2016 Presidential Campaign https://www.brookings.edu/book/words-that-matter/).