Exportar Publicação

Cardoso, A. S., Silva, C. da., Soriano-Redondo, A., Jarić, I., Batel, S., Santos, J. A....Vaz, A. S. (2025). Harnessing deep learning to monitor people’s perceptions towards climate change on social media. Scientific Reports. 15 (1)

A. S. Cardoso et al.,  "Harnessing deep learning to monitor people’s perceptions towards climate change on social media", in Scientific Reports, vol. 15, no. 1, 2025

@article{cardoso2025_1765129082873,
	author = "Cardoso, A. S. and Silva, C. da. and Soriano-Redondo, A. and Jarić, I. and Batel, S. and Santos, J. A. and Jorge, A. and Vaz, A. S.",
	title = "Harnessing deep learning to monitor people’s perceptions towards climate change on social media",
	journal = "Scientific Reports",
	year = "2025",
	volume = "15",
	number = "1",
	doi = "10.1038/s41598-025-97441-1",
	url = "https://www.nature.com/srep/"
}

TY  - JOUR
TI  - Harnessing deep learning to monitor people’s perceptions towards climate change on social media
T2  - Scientific Reports
VL  - 15
IS  - 1
AU  - Cardoso, A. S.
AU  - Silva, C. da.
AU  - Soriano-Redondo, A.
AU  - Jarić, I.
AU  - Batel, S.
AU  - Santos, J. A.
AU  - Jorge, A.
AU  - Vaz, A. S.
PY  - 2025
SN  - 2045-2322
DO  - 10.1038/s41598-025-97441-1
UR  - https://www.nature.com/srep/
AB  - Social media has become a popular stage for people’s views over climate change. Monitoring how climate change is perceived on social media is relevant for informed decision-making. This work advances the way social media users’ perceptions and reactions towards climate change can be understood over time, by implementing a scalable methodological framework grounded on natural language processing. The framework was tested in over 1771 thousand X/Twitter posts of Spanish, Portuguese, and English discourses from Southwestern Europe. The employed models were successful (i.e., > 84% success rate) in detecting relevant climate change posts. The methodology detected specific climate phenomena in users’ discourse, coinciding with the occurrence of major climatic events in the test area (e.g., wildfires, storms). The classification of sentiments, emotions, and irony was also efficient, with evaluation metrics ranging from 71 to 92%. Most users’ reactions were neutral (> 35%) or negative (> 39%), mostly associated to sentiments of anger and sadness over climate impacts. Almost a quarter of posts showed ironic content, reflecting the common use of irony in social media communication. Our exploratory study holds potential to support climate decisions based on deep learning tools from monitoring people’s perceptions towards climate issues in the online space.
ER  -