Public opinion surveys can measure county-level attitudes, opinions, and beliefs on climate change and the policies designed to mitigate its effects. Conducting large-scale population-based surveys is time consuming and expensive, but it’s important given that county-level belief in climate change ranges from 43-80% in the U.S. A new paper outlines a machine learning framework that maps social media discourse to climate opinion surveys to better understand the complexities of individual climate change beliefs. The researchers find that climate change opinions demonstrate clear regional differences, with a strong correlation between social media discourse and climate attitude—but in ways that are not always intuitive.
Bennett J., B. Rachunok, R. Flage, and R. Nateghi R (2021). Mapping climate discourse to climate opinion: An approach for augmenting surveys with social media to enhance understandings of climate opinion in the United States. PLoS ONE 16(1): e0245319.