Using large language models to learn from recent climate change discourse in public health.
<h4>Background</h4>Public health has increasingly recognized the links between climate change and health, emphasizing the need to address related inequities. This is reflected in work led by the Intergovernmental Panel on Climate Change, the UN Framework Convention on Climate Change, the...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0321309 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850269768145174528 |
|---|---|
| author | Anna Belova Raquel A Silva Dylan M Vorndran Natalie R Sampson |
| author_facet | Anna Belova Raquel A Silva Dylan M Vorndran Natalie R Sampson |
| author_sort | Anna Belova |
| collection | DOAJ |
| description | <h4>Background</h4>Public health has increasingly recognized the links between climate change and health, emphasizing the need to address related inequities. This is reflected in work led by the Intergovernmental Panel on Climate Change, the UN Framework Convention on Climate Change, the U.S. National Climate Assessment, and leading health-related professional associations, such as the American Public Health Association (APHA). We ask how the focus of climate change-related topics in public health discourse has evolved, and what does this signal about the field's role and capacity to address this global crisis?<h4>Methods</h4>We analyzed close to 41,000 abstracts from APHA annual meetings (2017-2023). Using a combination of large language models and expert review, we identified and analyzed over 1,100 abstracts with climate change-related content. We used a fine-tuned OpenAI GPT-3.5 model to detect abstracts with climate change-related content and the Claude 3.0 Sonnet model to categorize these abstracts into 21 themes and 12 health outcome categories.<h4>Results</h4>Since 2017, the discussion of climate change at APHA has declined both in terms of volume and topic diversity. The impacts of climate change on heat-related illness, stress and mental illness, and vector-borne diseases were the most common topics discussed. Fewer abstracts discussed the role of public health, workforce development, and policy and advocacy, with slightly more attention focused on health communication and education.<h4>Conclusions</h4>Although this is only a snapshot of recent discourse in the field, trends suggest the need to build capacity for climate action. Addressing the climate crisis is not solely an environmental health issue; it is a public health issue. Advocates, policymakers, and scholars know that innovative and intersectoral solutions are critical for effective and equitable climate action. However, within public health, we must work together and jointly contribute to reducing the unequal and extensive burdens associated with our changing climate. |
| format | Article |
| id | doaj-art-d8c545536b374b1da4e328f6f9d65e30 |
| institution | OA Journals |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-d8c545536b374b1da4e328f6f9d65e302025-08-20T01:52:58ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01204e032130910.1371/journal.pone.0321309Using large language models to learn from recent climate change discourse in public health.Anna BelovaRaquel A SilvaDylan M VorndranNatalie R Sampson<h4>Background</h4>Public health has increasingly recognized the links between climate change and health, emphasizing the need to address related inequities. This is reflected in work led by the Intergovernmental Panel on Climate Change, the UN Framework Convention on Climate Change, the U.S. National Climate Assessment, and leading health-related professional associations, such as the American Public Health Association (APHA). We ask how the focus of climate change-related topics in public health discourse has evolved, and what does this signal about the field's role and capacity to address this global crisis?<h4>Methods</h4>We analyzed close to 41,000 abstracts from APHA annual meetings (2017-2023). Using a combination of large language models and expert review, we identified and analyzed over 1,100 abstracts with climate change-related content. We used a fine-tuned OpenAI GPT-3.5 model to detect abstracts with climate change-related content and the Claude 3.0 Sonnet model to categorize these abstracts into 21 themes and 12 health outcome categories.<h4>Results</h4>Since 2017, the discussion of climate change at APHA has declined both in terms of volume and topic diversity. The impacts of climate change on heat-related illness, stress and mental illness, and vector-borne diseases were the most common topics discussed. Fewer abstracts discussed the role of public health, workforce development, and policy and advocacy, with slightly more attention focused on health communication and education.<h4>Conclusions</h4>Although this is only a snapshot of recent discourse in the field, trends suggest the need to build capacity for climate action. Addressing the climate crisis is not solely an environmental health issue; it is a public health issue. Advocates, policymakers, and scholars know that innovative and intersectoral solutions are critical for effective and equitable climate action. However, within public health, we must work together and jointly contribute to reducing the unequal and extensive burdens associated with our changing climate.https://doi.org/10.1371/journal.pone.0321309 |
| spellingShingle | Anna Belova Raquel A Silva Dylan M Vorndran Natalie R Sampson Using large language models to learn from recent climate change discourse in public health. PLoS ONE |
| title | Using large language models to learn from recent climate change discourse in public health. |
| title_full | Using large language models to learn from recent climate change discourse in public health. |
| title_fullStr | Using large language models to learn from recent climate change discourse in public health. |
| title_full_unstemmed | Using large language models to learn from recent climate change discourse in public health. |
| title_short | Using large language models to learn from recent climate change discourse in public health. |
| title_sort | using large language models to learn from recent climate change discourse in public health |
| url | https://doi.org/10.1371/journal.pone.0321309 |
| work_keys_str_mv | AT annabelova usinglargelanguagemodelstolearnfromrecentclimatechangediscourseinpublichealth AT raquelasilva usinglargelanguagemodelstolearnfromrecentclimatechangediscourseinpublichealth AT dylanmvorndran usinglargelanguagemodelstolearnfromrecentclimatechangediscourseinpublichealth AT nataliersampson usinglargelanguagemodelstolearnfromrecentclimatechangediscourseinpublichealth |