Online Program

HR viewer: A tool for visualizing sentiment of u.s. health care reform

Wednesday, November 6, 2013 : 11:30 a.m. - 11:50 a.m.

Beatrice Abiero, BS, Health Policy and Administration and Demography, The Pennsylvania State University, University Park, PA
Ryan Mullins, BS, Department of Geography, The Pennsylvania State University, University Park, PA
Kim Na, BA, School of International Affairs, The Pennsylvania State University, University Park, PA
Andrew Gladfelter, BS, Department of Sociology and Crime, Law, and Justice, The Pennsylvania State University, University Park, PA
Sam Stehle, M.S., Department of Geography Penn State University, University Park, PA
Background. The passage of health reform has sparked political and social discourse that warrants further study in regards to public sentiment. This study contributes to the social science literature by exploring how social media data can inform the understanding of public opinions about health reform, while using integrated visual and computational methods including geovisualization and data mining. Methods. This project conducts sentiment analysis of public opinions from social media with a novel web based visualization tool “HR Viewer” developed specifically for this study. Data were collected from the popular microblog Twitter, during the week of the 2012 presidential election, and analyzed for sentiment using previously validated algorithms. In order to examine variation in sentiment by state level characteristics, other data including demographic, economic, political affiliation, polling, and health data were imported into HR Viewer. Results. Based on n=238 tweets, sentiment in the U.S. towards PPACA appears to be neutral to slightly positive; however, regional variation in sentiment was not evident. States with higher proportions of disabled individuals, obesity, unemployment, uninsured individuals, Republicans or Democrats appear no more likely to favor PPACA than those with lower levels. Conclusions. This tool serves as a proof of concept that sentiment analysis is possible with social media data and could be applied to larger samples. Future research directions include applying the HR Viewer to a larger sample of geotagged twitter data that expands from October 2011 to March 2012, and aggregating at the county level.

Learning Areas:

Public health or related research
Social and behavioral sciences

Learning Objectives:
Demonstrate how to use social media to explore public sentiment of health reform.

Presenting author's disclosure statement:

Qualified on the content I am responsible for because: I am a student collaborator on this project and assisted in the development of this project.
Any relevant financial relationships? No

I agree to comply with the American Public Health Association Conflict of Interest and Commercial Support Guidelines, and to disclose to the participants any off-label or experimental uses of a commercial product or service discussed in my presentation.