Table 1.
Categories from LDA topic analysis and a brief summary of their content.
Fig 1.
Distribution of Consolidated Climate Opinion (CCO) and Twitter users in the United States.
(a) County-level CCO, calculated as the principal component reduction of 14 survey questions collected in the Yale Climate Opinion Dataset [1]. (b) County-level distribution of Tweet Density (tweets / person, log scale) in the United States based on climate-related tweets collected using the Twitter API from April 18th through April 25th, 2019.
Table 2.
Model performance based on Normalized Root Mean Square Error (NRMSE) and R2 for each regional model.
Fig 2.
Regional Twitter topic distributions.
Each region of the US used in this analysis is shown along with its corresponding most important LDA topics. Topics are listed in order of their importance (top to bottom), and colored based on how frequently they occur in regional discussion: darker is more unique to the region while lighter is more common nationally.
Fig 3.
Partial dependence plots of topics and CCO.
Each plot shows how CCO changes with an increase in a given Twitter topic while controlling for other variables. Shaded regions around line indicate a 97.5% confidence interval.