Authors: Matthew Cooper*, University of Maryland, Jeremiah Osborne-Gowey, Environmental Studies Program, University of Colorado Boulder USA, Zheng Liu, Geographical Sciences, University of Maryland USA, Jie Liu, Management Science, East China University of Science and Technology , Portia Williams, Environmental and Geographical Science, University of Cape Town
Topics: Hazards and Vulnerability, Environment, Geographic Information Science and Systems
Keywords: Text Data, Environmental Shocks, Climate Shocks, Public Opinion, Perception, Sentiment, Media, News, Social Media, Twitter, Climate Change, Science Communication, Policy, Planning, Methods, Text Mining, Social Media Mining, Natural Language Processing, Sentiment Analysis, Political Ecology, Politics, Resilience, Adaptation
Session Type: Virtual Paper
Start / End Time: 3:05 PM / 4:20 PM
Room: Virtual 44
Presentation File: No File Uploaded
Weather can affect people’s mood and well-being. Traditional studies exploring the effects of weather on mental health require significant amounts of time to plan, fund and execute. Continuous in situ data streams from social media, newspapers, and other big data sources offer an opportunity to examine how people perceive and respond to environmental conditions. Recent work demonstrates that prevailing weather conditions can affect people’s sentiment as expressed on Twitter and other social media. Studies to date however, have modeled the weather as having the same aggregate effect on sentiment across all locations and individuals. In this study, we explore how weather affects individual expressed sentiment on Twitter across different weather gradients and locations. We analyzed the sentiment from a quarter of a billion geolocated Tweets from 2009 to 2019, using multiple measures of sentiment, overlaid with data about prevailing weather conditions, as well as local land cover, income levels, and demographic characteristics in the vicinity of Twitter users. Initial results suggest that local conditions can have strong affects on how weather affects twitter sentiment. This project extends existing research about the relationship between temperature and mood by examining how varying climatic conditions across different geographies and socio-economic groups are correlated with expressed sentiment. This project brings new insights into how humans perceive and respond to environmental shocks, with important implications for economics, policy and adaptation and resilience planning.