CAREER: Promoting Equal Opportunities through Measurement, Simulation, and Education

Suny At Buffalo, Amherst NY

Investigators

Abstract

This research will advance our ability to draw on large-scale data from online social media to understand attitudes towards social issues in the United States and their correlations with critical dimensions of social structure. The planned advances in large-scale computational social science research methods will allow researchers to improve existing theories of attitude formation and influence by (a) adapting them to a wide variety of online communication systems and (b) incorporating information that is available online about location, demographics, and network structure. The long-term research goal is to expand knowledge on how computational methods can be constructively used alongside social theory and large datasets to help understand social differences in attitudes and inform research, policy, and design of the systems people use to talk about them. The work will include the development and release of tools aimed at making the methods more accessible to scholars without extensive computational training. The project will also advance computer science education via the development of new curriculum and opportunities for undergraduate research. This project has four fundamental research objectives. First, the project team will develop novel mixed methods approaches that combine modern graph-based and natural language machine learning methods with qualitative analysis to identify dominant beliefs about social issues expressed in large datasets from X and Parler. Second, the team will collect and analyze an innovative new dataset linking social media and survey data on attitudes about social issues, providing insight into discrepancies between these two sources of measurement. Third, the researchers will combine measurements of social media users' views on these issues with data on where they live and the structure of their social networks to study how place, identity, and network structure are correlated with people's attitudes. Fourth, the project team will develop a novel agent-based simulation framework that combines empirical findings with contemporary theory on social attitudes, that can be used to evaluate the strengths and weaknesses of different proposed interventions and designs for online communication systems. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.