Survey research has long been a bedrock for understanding society and its needs. Social media data collected from, for example, Twitter users is providing new ways to perform social science research and, for some research questions, may be a viable supplement to or replacement for survey data. However, to understand what can and cannot be inferred from Twitter data, it is critical to understand who is using Twitter. Toward that end, two questions of interest include: “How different are Twitter users from the general population?” and “Do Twitter use rates vary by states and region?” Answering both of these questions is important to justify the use of Twitter data for generalizable social science research.
To date, estimates of the prevalence and characteristics of Twitter users have been provided only at the national level. To provide a richer picture of this population, the MOSAIC project has been investigating methods for producing estimates of Twitter use at the state level. This methodology brief provides preliminary state-level estimates and information about how they are produced.
Suggested Citation: Jackson, M. McKinstry, J., McPhee, C., Raghunathan, T., Singh, L., Traugott, M., Turakhia, C. & Wycoff, N. (2021). Understanding who uses Twitter: State level estimates of those on Twitter. MOSAIC Methods Brief: November 2021. Measuring Online Social Attitudes and Information Collaborative
