EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Stay Tuned: Improving Sentiment Analysis and Stance Detection Using Large Language Models

Max Griswold, Michael W. Robbins, Michael S. Pollard

Political Analysis · 2026-07 · 34 (3) · 392-411

DOI: 10.1017/pan.2025.10023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Political Analysis, online erschienen am 17.12.2025. Verfasst von Max Griswold und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Division of Information and Intelligent Systems.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sentiment analysis and stance detection are key tasks in text analysis, with applications ranging from understanding political opinions to tracking policy positions. Recent advances in large language models (LLMs) offer significant potential to enhance sentiment analysis techniques and to evolve them into the more nuanced task of detecting stances expressed toward specific subjects. In this study, we evaluate lexicon-based models, supervised models, and LLMs for stance detection using two corpuses of social media data—a large corpus of tweets posted by members of the U.S. Congress on Twitter and a smaller sample of tweets from general users—which both focus on opinions concerning presidential candidates during the 2020 election. We consider several fine-tuning strategies to improve performance—including cross-target tuning using an assumption of congressmembers’ stance based on party affiliation—and strategies for fine-tuning LLMs, including few shot and chain-of-thought prompting. Our findings demonstrate that: 1) LLMs can distinguish stance on a specific target even when multiple subjects are mentioned, 2) tuning leads to notable improvements over pretrained models, 3) cross-target tuning can provide a viable alternative to in-target tuning in some settings, and 4) complex prompting strategies lead to improvements over pretrained models but underperform tuning approaches.

Förderung

  • Division of Information and Intelligent Systems

Zitieren

APA

Griswold, M., Robbins, M. W., & Pollard, M. S. (2026). Stay Tuned: Improving Sentiment Analysis and Stance Detection Using Large Language Models. Political Analysis, 34(3), 392-411. https://doi.org/10.1017/pan.2025.10023

Vancouver

Griswold M, Robbins MW, Pollard MS. Stay Tuned: Improving Sentiment Analysis and Stance Detection Using Large Language Models. Political Analysis. 2026;34(3):392-411. doi:10.1017/pan.2025.10023

BibTeX
@article{Griswold2026,
  author = {Griswold, Max and Robbins, Michael W. and Pollard, Michael S.},
  title = {Stay Tuned: Improving Sentiment Analysis and Stance Detection Using Large Language Models},
  journal = {Political Analysis},
  year = {2026},
  volume = {34},
  number = {3},
  pages = {392--411},
  doi = {10.1017/pan.2025.10023}
}
Kostenlos starten →