Measuring the Effects of Peer Sharing on Fake and Polarized News Consumption
Why do people consume and share fake news online? Previous work has shown that news consumption and sharing emerges from complex interactions among news sources, news content, and user characteristics: users consume and share ideologically aligned news and shun the opposite. This behavior is further complicated by fake news, which can amplify content’s ideological and emotional characteristics without the constraints of truth, and by peer sharing, which may reduce institutional barriers to fake news and amplify local, peer-to-peer polarization. Identifying the mechanisms by which peers amplify fake and polarized news remains challenging, however, because social media has coevolved with polarization and shifts in the news media landscape. To illuminate these mechanisms, we begin by developing new natural language processing (NLP) methods to measure the ideology and emotion of news content and to assess how ideology and emotion of news content affect sharing and consumption. Having established this baseline, we then exploit a natural discontinuity to identify specifically peer-related effects on sharing: recent public changes in the Facebook algorithm abruptly shifted the balance between peer- and media-sourced news, allowing us to use difference-in-difference and other longitudinal estimators to measure changes in polarized or fake news and discover how peer-sharing affects these tendencies. This combination of NLP, network, and discontinuity approaches should provide unique insights into the interactions between news, ideology, falsity, and peer sharing, and shed light on important questions such as how social media may have affected polarization, fake news, and political knowledge in the recent era.
Assistant Professor of Political Science, Northeastern University
Nicholas Beauchamp is an assistant professor at Northeastern University in the Department of Political Science and a core faculty member of the Network Science Institute and the NULab for Text, Maps, and Networks. His research uses techniques from natural language processing, machine learning, Bayesian statistics, and network analysis to examine how discussion, argument, and deliberation affect political opinion in domains such as legislatures, campaigns, the judiciary, and social media. Recent work has included using Twitter data to model deliberation and to predict political polls; tracing hate language evolution in individuals online; modeling and visualizing political debates; using neural networks to predict votes from bill text; and algorithmically generated persuasive text. He is currently working on a larger series of projects that model political deliberation as the strategic exchange of ideas drawn from complex mental networks of interlinked beliefs.
Distinguished Professor of Political Science and Computer and Information Science, Northeastern University
David Lazer is a professor of political science and computer and information science and the codirector of the NULab for Texts, Maps, and Networks. Before joining the Northeastern faculty in fall 2009, he was an associate professor of public policy at Harvard’s John F. Kennedy School of Government and director of its Program on Networked Governance. He holds a PhD in political science from the University of Michigan. Professor Lazer’s research centers on social networks; governance, or how the patterns of institutional relations yield functional or dysfunctional systems; and technology and its use in communication. An authority on social networks, he has written several papers on the diffusion of information among interest groups and between these groups and the government. He is the coeditor of Governance and Information Technology: From Electronic Government to Information Government and has also written extensively on the use of DNA in the criminal justice system.
Assistant Professor of Economics, Northeastern University
Donghee Jo is an assistant professor of economics at Northeastern University. He is a faculty affiliate with the Network Science Institute and NULab for Texts, Maps, and Networks. He specializes in political economy and development economics, and the current primary focuses of his research are political polarization in developed nations and propaganda in developing nations with nondemocratic regimes. He has led several experimental studies online—he developed a mobile news application and distributed this app to the general public of South Korea to experimentally study the effect of selective exposure to like-minded media. He also successfully ran an experiment in collaboration with BallotReady.org, a website that provides information about the candidates of elections in United States. BallotReady.org had 3.8 million unique users in the 2018 US general election, among which approximately 1 million users were included as experimental subjects. His works have been funded by the Abdul Latif Jameel Poverty Action Lab and Laura and John Arnold Foundation, and one of his works has appeared in the Washington Post. More information about him can be found at http://dongheejo.com/.
Assistant Professor of Computer Science and Engineering, State University of New York at Buffalo
Kenneth (Kenny) Joseph is an assistant professor in the Computer Science and Engineering Department at the University at Buffalo. Prior to that, he was a postdoc at Northeastern's Network Science Institute and a fellow at Harvard's Institute for Quantitative Social Science, and completed his PhD in societal computing at Carnegie Mellon University. His research interests include quantitative modeling of stereotypes and prejudice, and how such biases are obtained via social and traditional news media. Recent work has appear in a range of publications, including Science, WWW, and New Media & Society. You can find more information on his work at his website, http://kennyjoseph.github.io/.
Assistant Professor of Computer Science, Northeastern University
Lu Wang is an assistant professor in Khoury College of Computer and Information Sciences at Northeastern University. She received her PhD in Computer Science from Cornell University and her bachelor’s degrees in intelligent science and technology and economics from Peking University. Her research mainly focuses on designing machine learning algorithms and statistical models for natural language processing (NLP) tasks, including abstractive text summarization, language generation, argument mining, information extraction, and their applications in interdisciplinary subjects (e.g., computational social science). Wang received an outstanding short paper award at ACL 2017 and a best paper nomination award at SIGDIAL 2012. Her group's work is funded by National Science Foundation (NSF), Intelligence Advanced Research Projects Activity (IARPA), and several industry gifts. More information about her research can be found at www.ccs.neu.edu/home/luwang/.