Healthcare (Commonwealth Union) – Rising global heat influences human behavior in many ways. A recent study highlights a new aspect of this issue: extremely hot days are linked to a noticeable increase in negative emotions, according to a large-scale analysis of social media content.
The research reviewed 1.2 billion posts from 157 countries over the course of a year. It found that when temperatures exceeded 95°F (35°C), online expressions of sentiment became around 25% more negative in lower-income nations and about 8% more negative in wealthier ones. This shows that extreme heat impacts people’s emotional state as well as their physical health.
Siqi Zheng, professor in MIT’s Department of Urban Studies and Planning (DUSP) and Center for Real Estate (CRE), and co-author of a newly released study indicated that their research shows that rising heat does not just put physical health or economic performance at risk — it also influences people’s emotions, every single day, across the globe.
She further indicated that the study opens an important new direction in understanding how climate-related stress is impacting human well-being worldwide.
The study, titled “Unequal Impacts of Rising Temperatures on Global Human Sentiment,” was published recently in the journal One Earth. Its authors include Jianghao Wang of the Chinese Academy of Sciences; Nicolas Guetta-Jeanrenaud SM ’22, a graduate of MIT’s Technology and Policy Program (TPP) and Institute for Data, Systems, and Society; Juan Palacios, a visiting assistant professor at MIT’s Sustainable Urbanization Lab (SUL) and assistant professor at Maastricht University; Yichun Fan of SUL and Duke University; Devika Kakkar of Harvard University; Nick Obradovich of SUL and the Laureate Institute for Brain Research in Tulsa; and Zheng, who is the STL Champion Professor of Urban and Real Estate Sustainability at CRE and DUSP. Zheng also directs the CRE as faculty lead and founded the Sustainable Urbanization Lab in 2019.
The research involved, the evaluation by the team of 1.2 billion social media posts from Twitter and Weibo, all published in 2019. They used a natural language processing technique known as Bidirectional Encoder Representations from Transformers (BERT) to look into content in 65 languages across 157 countries.
Every single post got a sentiment score ranging from 0.0, demonstrating a highly negative sentiment, to 1.0, showing a highly positive sentiment. The posts were then grouped by 2,988 geographic areas and contrasted with local weather data. This approach made it possible for the researchers to identify connections between extreme temperatures and the sentiments expressed online.
Wang pointed out that social media offers an unparalleled view into human emotions across cultures and regions.
He further indicated that by applying this method, they can track the emotional consequences of climate change on a scale that traditional surveys simply are unable to match, providing near real-time insight into how temperature influences mood around the world.
To look into the way temperature affects sentiment in various economic contexts, the researchers categorized nations using the World Bank threshold of $13,845 per capita annual income. They noted that in regions under this income level, the impact of heat on mood was three times more than in wealthier areas.
“Thanks to the global coverage of our data, we find that people in low- and middle-income countries experience sentiment declines from extreme heat that are three times greater than those in high-income countries,” explained Fan. “This underscores the importance of incorporating adaptation into future climate impact projections.”
Using long-term global climate models and accounting for potential adaptation to heat, the researchers generated a projection of how extreme temperatures could influence sentiment by 2100. Extrapolating their current findings, they estimate that high temperatures alone could reduce people’s emotional well-being by about 2.3 percent by the end of the century — though they note that this is a long-term projection and carries uncertainty.
