Dataset Information

Mapping climate discourse to climate opinion: An approach for augmenting surveys with social media to enhance understandings of climate opinion in the United States.

ABSTRACT: Surveys are commonly used to quantify public opinions of climate change and to inform sustainability policies. However, conducting large-scale population-based surveys is often a difficult task due to time and resource constraints. This paper outlines a machine learning framework-grounded in statistical learning theory and natural language processing-to augment climate change opinion surveys with social media data. The proposed framework maps social media discourse to climate opinion surveys, allowing for discerning the regionally distinct topics and themes that contribute to climate opinions. The analysis reveals significant regional variation in the emergent social media topics associated with climate opinions. Furthermore, significant correlation is identified between social media discourse and climate attitude. However, the dependencies between topic discussion and climate opinion are not always intuitive and often require augmenting the analysis with a topic's most frequent n-grams and most representative tweets to effectively interpret the relationship. Finally, the paper concludes with a discussion of how these results can be used in the policy framing process to quickly and effectively understand constituents' opinions on critical issues.

SUBMITTER: Bennett J

PROVIDER: S-EPMC7808624 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Mapping climate discourse to climate opinion: An approach for augmenting surveys with social media to enhance understandings of climate opinion in the United States.

Bennett Jackson J Rachunok Benjamin B Flage Roger R Nateghi Roshanak R

PloS one 20210114 1

Surveys are commonly used to quantify public opinions of climate change and to inform sustainability policies. However, conducting large-scale population-based surveys is often a difficult task due to time and resource constraints. This paper outlines a machine learning framework-grounded in statistical learning theory and natural language processing-to augment climate change opinion surveys with social media data. The proposed framework maps social media discourse to climate opinion surveys, al ...[more]

PMID: 33444371

Similar Datasets

Project description:Despite ongoing calls for a more even global distribution of COVID-19 vaccines, there remains a great disparity between high- and low-income countries. We conducted representative surveys among the adult populations in the United States (N = 1,000) and Germany (N = 1,003) in June 2021 to assess public opinion in these countries on the distributive justice of COVID-19 vaccines. We conducted two instances of analytic hierarchy processes (AHP) to elicit how the public weighs different principles and criteria for vaccine allocation. In further discrete choice experiments, respondents were asked to split a limited supply of vaccine doses between a hypothetical high-income and a hypothetical low-income country. AHP weights in the United States and Germany were 37.4% (37.2-37.5) and 49.4% (49.2-49.5) for "medical urgency", 32.7% (32.6-32.8) and 25.4% (25.2-25.5) for "equal access for all", 13.7% (13.6-13.8) and 13.3% (13.2-13.4) for "production contribution", and 16.3% (16.2-16.4) and 12.0% (11.9-12.1) for "free market rules", respectively, with 95% CI shown in parentheses. In the discrete choice experiment, respondents in the United States and Germany split available vaccine doses such that the low-income country, which was three times more populous than the high-income country, on average received 53.9% (95% CI: 52.6-55.1) and 57.5% (95% CI: 56.3-58.7) of available doses, respectively. When faced with a dilemma where a vulnerable family member was waiting for a vaccine, 20.7% (95% CI: 18.2-23.3) of respondents in the United States and 18.2% (95% CI: 15.8-20.6) in Germany reduced the amount they allocated to the low-income country sufficiently to secure a vaccine for their family member. Our results indicate that the public in the United States and Germany favours utilitarian and egalitarian distribution principles of vaccines for COVID-19 over libertarian or meritocratic principles. This implies that political decisions favouring higher levels of redistribution would be supported by public opinion in these two countries.

Dataset Information

Mapping climate discourse to climate opinion: An approach for augmenting surveys with social media to enhance understandings of climate opinion in the United States.

Publications

Mapping climate discourse to climate opinion: An approach for augmenting surveys with social media to enhance understandings of climate opinion in the United States.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets