Our study, entitled “Supplementing Survey-Based Analyses of Group Vaccination Narratives and Behaviors Using Social Media” is developing a new and complementary research methodology to better understand people’s attitudes, beliefs and behaviors related to vaccination.
Using sophisticated computer algorithms, demographic and geolocation identifiers, and the scale of Big Data, we will compare existing survey data to Twitter conversations about vaccination.
Our goal is to analyze these Twitter conversations with the same rigor and accuracy as we can currently analyze survey data. Not only is this methodology faster and less expensive than traditional survey research, but it will provide greater understanding of the relatively younger, more urban and more racially diverse users of social media, who tend to be under-represented in traditional survey data gathering.
Eventually, we hope to be able to analyze social media data with rigor in real time, overcoming a critical communication challenge for public health officials in evolving public health crises.
We are currently testing the methodology in the area of vaccination attitudes and behaviors, but encourage use of our technique for other public health issues.
Principal Investigator David Broniatowski PhD. is an Assistant Professor at George Washington University and has his PhD from Massachusetts Institute of Technology (MIT). He conducts research in decision-making under risk, group decision-making, system architecture, and behavioral epidemiology. His research draws upon a wide range of techniques including formal mathematical modeling, experimental design, automated text analysis and natural language processing, social and technical network analysis, and big data. His current projects include a text network analysis of transcripts from the US Food and Drug Administration’s Circulatory Systems Advisory Panel meetings, a mathematical formalization of Fuzzy Trace Theory — a leading theory of decision-making under risk, derivation of metrics for flexibility and controllability for complex engineered socio-technical systems, and using Twitter data to conduct surveillance of influenza infection and the resulting social response.
Principal Investigator Sandra Crouse Quinn, PhD. is an Associate Dean for Academic Affairs Senior Associate Director, at the Maryland Center for Health Equity Professor, in the Department of Family Science School of Public Health at the University of Maryland.
Co-Investigator Mark Dredze, PhD. is an assistant research professor of computer science at Johns Hopkins University. He primarily works in the Human Language Technology Center of Excellence (HLTCOE). He is affiliated with the Center for Speech and Language Processing (CLSP) and is part of the Machine Learning Group. He leads the Social Media and Health Research Group. His research interests include: machine learning, natural language processing, social media and health informatics.
Co-Investigator Josh Epstein, PhD. is a professor of emergency medicine and has dual appointments in the Department of Economics and the Department of Biostatistics, and Environmental Health at Johns Hopkins University.Epstein also serves as an External Professor at the Santa Fe Institute and a member of the New York Academy of Sciences and is a former Senior Fellow in Economics and Director of the center of Social and Economic Dynamics at the Brookings Institution. He is also the director of Global Epidemic Modeling for the National Institutes of Health’s Models of Infectious Disease Agent Study (MIDAS), and is part of a collaboration of research and informatics groups to develop computational models of infectious agents and control strategies.
Co-Investigator Eili Klein, PhD. is a fellow at the Center for Disease Dynamics, Economics, and Policy. Dr. Klein is a mathematical ecologist and epidemiologist whose research focuses on the role of behavior in the spread of infectious diseases. Examining how individuals respond to incentives for both healthy and unhealthy behavior – an area which economics has a lot to say – and how this then impacts the spread disease can improve policy responses to epidemic diseases by giving policymakers and health-care providers clear tools for thinking about how certain actions can influence the spread of disease transmission.
Postdoctoral Investigator Tao Chen is a postdoc in the Computer Science department at Johns Hopkins University. She received her PhD in Computer Science from the National University of Singapore in 2016. Her thesis studied how images were shared and used on social media.
Student Investigator Dian Hu is a Ph.D. student in the Systems Engineering program at the George Washington University’s School of Engineering and Applied Science. Dian earned his Bachelor of Science degree in Systems Engineering from the GW with honors. In his first job before graduate study, Dian worked on several projects involving data visualization, data migration and web-based application development. Dian’s academic interests are Big Data and Health, Rumor Spreading Mechanisms, Influenza, Risky Decision Models, Machine Learning, and Natural Language Processing.
Student Investigator Michael C. Smith is a Ph.D. student in the Systems Engineering department at the George Washington University’s School of Engineering and Applied Science. Michael earned his bachelor’s and master’s degrees from the Computer Science department at the Johns Hopkins University, concentrating on natural language processing and machine learning. His past experience includes stints at IBM Global Business Services, IBM Watson, and JHU’s Human Language Technology Center of Excellence. Currently, Michael’s interests lie where public health and text analysis intersect: generating and leveraging big data from social media to further behavioral epidemiology and the models therein of decision-making under risk.
Student Investigator Adrian Benton is a Ph.D. student in the Computer Science department at Johns Hopkins University. He has previously conducted research on using social media for public health. His role on the project is to develop new natural language processing and machine learning algorithms that mine social media data.
Student Investigator Zachary Wood-Doughty is a Ph.D. student in the Computer Science department at Johns Hopkins University. His role on the project is to develop new natural language processing and machine learning algorithms that analyze social media user behavior.
Student Investigator Yuki Lama is a Ph.D. student in Maternal and Child Health in the Family Science Department at the University of Maryland’s School of Public Health. Her role on the project is providing support to social science research efforts related to vaccine behavior, particularly around HPV vaccine uptake.
Investigator Amelia Jamison is a faculty research assistant with the Maryland Center for Health Equity at the University of Maryland. She has an M.A. in applied anthropology and an M.P.H. in epidemiology, both from the University of Maryland. Her role in the project is on the social science team as an vaccination subject matter expert.
We are funded from February 2015-2020 by a $1.6 million grant from the National Institutes of Health (NIH) National Institute for General Medical Sciences (NIGMS), via award 1R01GM114771-01.