Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 1.40 MB
Add to list
  1. Search results
  2. Geosocial media’s perspective on ener...

Geosocial media’s perspective on energy : a text classification approach using natural language processing

Jana Verdoodt (UGent) , Kenzo Milleville (UGent) , Haosheng Huang (UGent) , Christophe Vandeviver (UGent) , Steven Verstockt (UGent) and Nico Van de Weghe (UGent)
(2025) JOURNAL OF LOCATION BASED SERVICES.
Author
Organization
Project
Abstract
This study examines public opinion on various energy sources through Twitter data, focusing on fossil fuels, nuclear energy, and renewable energy sources like solar and wind. Utilizing natural language processing techniques, specifically BERTweet and GPT models, the research analyses tweet categorization based on sentiment and stance related to these energy sources. Our findings reveal a positive shift towards nuclear, solar, and wind energy, contrasting with increasing negative sentiment towards fossil fuels. Notably, BERTweet demonstrates superior precision and recall in tweet categorization compared to GPT-3.5 and GPT-4, which show potential bias against fossil fuels, misclassifying many tweets as opposing them. This study highlights the importance of social media analytics in understanding public opinions and shaping energy policy, suggesting that future research should broaden the scope of data, enhance multilingual capabilities, and improve data visualization to more accurately reflect global public opinion. The results underscore the need for balanced AI training to mitigate bias and more accurately capture diverse perspectives on contentious energy topics. The datasets, code utilized, and interactive maps with word clouds are available at https://doi.org/10.5281/zenodo.15020578 and https://doi.org/10.5281/zenodo.15084294.
Keywords
Geospatial data, social media, natural language processing, text classification, public opinion

Downloads

  • Download
    Verdoodt-et-al 2025.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.40 MB

Citation

Please use this url to cite or link to this publication:

MLA
Verdoodt, Jana, et al. “Geosocial Media’s Perspective on Energy : A Text Classification Approach Using Natural Language Processing.” JOURNAL OF LOCATION BASED SERVICES, 2025, doi:10.1080/17489725.2025.2501632.
APA
Verdoodt, J., Milleville, K., Huang, H., Vandeviver, C., Verstockt, S., & Van de Weghe, N. (2025). Geosocial media’s perspective on energy : a text classification approach using natural language processing. JOURNAL OF LOCATION BASED SERVICES. https://doi.org/10.1080/17489725.2025.2501632
Chicago author-date
Verdoodt, Jana, Kenzo Milleville, Haosheng Huang, Christophe Vandeviver, Steven Verstockt, and Nico Van de Weghe. 2025. “Geosocial Media’s Perspective on Energy : A Text Classification Approach Using Natural Language Processing.” JOURNAL OF LOCATION BASED SERVICES. https://doi.org/10.1080/17489725.2025.2501632.
Chicago author-date (all authors)
Verdoodt, Jana, Kenzo Milleville, Haosheng Huang, Christophe Vandeviver, Steven Verstockt, and Nico Van de Weghe. 2025. “Geosocial Media’s Perspective on Energy : A Text Classification Approach Using Natural Language Processing.” JOURNAL OF LOCATION BASED SERVICES. doi:10.1080/17489725.2025.2501632.
Vancouver
1.
Verdoodt J, Milleville K, Huang H, Vandeviver C, Verstockt S, Van de Weghe N. Geosocial media’s perspective on energy : a text classification approach using natural language processing. JOURNAL OF LOCATION BASED SERVICES. 2025;
IEEE
[1]
J. Verdoodt, K. Milleville, H. Huang, C. Vandeviver, S. Verstockt, and N. Van de Weghe, “Geosocial media’s perspective on energy : a text classification approach using natural language processing,” JOURNAL OF LOCATION BASED SERVICES, 2025.
@article{01JXCSKKRYY150X2TAW5YHTSEG,
  abstract     = {{This study examines public opinion on various energy sources through Twitter data, focusing on fossil fuels, nuclear energy, and renewable energy sources like solar and wind. Utilizing natural language processing techniques, specifically BERTweet and GPT models, the research analyses tweet categorization based on sentiment and stance related to these energy sources. Our findings reveal a positive shift towards nuclear, solar, and wind energy, contrasting with increasing negative sentiment towards fossil fuels. Notably, BERTweet demonstrates superior precision and recall in tweet categorization compared to GPT-3.5 and GPT-4, which show potential bias against fossil fuels, misclassifying many tweets as opposing them. This study highlights the importance of social media analytics in understanding public opinions and shaping energy policy, suggesting that future research should broaden the scope of data, enhance multilingual capabilities, and improve data visualization to more accurately reflect global public opinion. The results underscore the need for balanced AI training to mitigate bias and more accurately capture diverse perspectives on contentious energy topics. The datasets, code utilized, and interactive maps with word clouds are available at https://doi.org/10.5281/zenodo.15020578 and https://doi.org/10.5281/zenodo.15084294.}},
  author       = {{Verdoodt, Jana and Milleville, Kenzo and Huang, Haosheng and Vandeviver, Christophe and Verstockt, Steven and Van de Weghe, Nico}},
  issn         = {{1748-9725}},
  journal      = {{JOURNAL OF LOCATION BASED SERVICES}},
  keywords     = {{Geospatial data,social media,natural language processing,text classification,public opinion}},
  language     = {{eng}},
  pages        = {{26}},
  title        = {{Geosocial media’s perspective on energy : a text classification approach using natural language processing}},
  url          = {{http://doi.org/10.1080/17489725.2025.2501632}},
  year         = {{2025}},
}
Altmetric
View in Altmetric