Sentiment analysis of solar energy in U.S. Cities: a 10-year analysis using transformer-based deep learning

Serena Y. Kim (), Crystal Soderman () and Lan Sang ()
Additional contact information
Serena Y. Kim: North Carolina State University
Crystal Soderman: University of Colorado Denver
Lan Sang: University of Colorado Boulder

Journal of Computational Social Science, 2025, vol. 8, issue 2, No 12, 26 pages

Abstract: Abstract This study examines U.S. public sentiment toward solar energy from 2013 to 2022 by analyzing 8 million social media posts using RoBERTa, a transformer-based deep learning algorithm. While sentiment has been generally positive, it has declined since 2016, driven by increasing negativity. The analysis reveals significant and widening regional disparities, with Republican-leaning and Southern U.S. regions showing more pronounced negativity. A two-way fixed-effects panel analysis at the municipality level indicates that positive sentiment is associated with high solar radiation and a larger remote-working population, while negative sentiment is linked to a greater prevalence of multifamily housing. These results highlight the complex interplay of environmental, socioeconomic, political, and technological factors in shaping solar energy sentiment and underscore the need for tailored, region-specific strategies. The computational approach, which combines natural language processing and geospatial analysis of social media data, provides a scalable framework for sentiment analysis across diverse topics and regions, extending beyond the specific case of solar energy in the United States.

Keywords: Natural language processing; Sentiment analysis; Geospatial analysis; Solar energy; Deep learning applications (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s42001-025-00365-z Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jcsosc:v:8:y:2025:i:2:d:10.1007_s42001-025-00365-z

Ordering information: This journal article can be ordered from
http://www.springer. ... iences/journal/42001

DOI: 10.1007/s42001-025-00365-z

Access Statistics for this article

Journal of Computational Social Science is currently edited by Takashi Kamihigashi

More articles in Journal of Computational Social Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().