Abstract
Media such as Twitter have become platforms for contemporary Americans to express their opinions and allow for reaction to public opinion. Climate change is a topic of ongoing social concern. Machine-automated processing facilitates “big data” analysis and is suitable for analyzing a large corpus of tweets. This paper uses R tools to conduct sentiment calculation and emotion analysis on the tweet corpus from 2015 to 2018 to present the overall tendency of citizens’ attitudes toward climate change topics. The keyword analysis finds that people focus on the message’s source. “Climate change” has often been conflated with “global warming” in the popular consciousness. Supporters of the scientific consensus that human activities drastically affect Earth’s climate system express fear and surprise about extreme weather and opponents’ behavior, whereas opponents of that consensus express multiple emotional responses that include anger, disgust, and sadness toward politicians who, in their view, fabricate stories about climate change about which they have no real feelings. This study also reveals that the automatic annotation tools are still inadequate, with limited emotion lexicon and identification of negation and sarcasm.
Significance Statement
This research aims to perceive people’s emotional expressions on climate change as expressed on Twitter. The distributions of emotions across different opinion groups on climate change can be analyzed by manually annotating the opinion stances. Our first step is to research keywords to identify the main discussion topics. Then, automatic sentiment analysis with R software reveals the prevalent negative positions, and emotion analysis yields the primary emotions and the connection with different opinion groups, which logistic regression models test. These results better reflect the concerns of the population and provide support for climate policy. Future research could subdivide topics and develop field-specialized sentiment and emotion lexicons.
© 2023 American Meteorological Society. For information regarding reuse of this content and general copyright information, consult the AMS Copyright Policy (www.ametsoc.org/PUBSReuseLicenses).
