Promises and pitfalls of using LLMs to identify actor stances in political discourse
PLOS One · 2025
DOI: 10.1371/journal.pone.0335547 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Viviane Walker und 1 weiteren Autor:innen. Beteiligte Einrichtung: University of Zürich, Zürich, Switzerland. Hauptthemen laut MEDLINE: Politics, Language. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Digitalisierungsinitiative der Zürcher Hochschulen.
Abstract (Originalsprache)
Empirical research in the social sciences is often interested in understanding actor stances; the positions that social actors take regarding normative statements in societal discourse. In automated text analysis applications, the classification task of stance detection remains challenging. Stance detection is especially difficult due to semantic challenges such as implicitness or missing context but also due to the general nature of the task. In this paper, we explore the potential of Large Language Models (LLMs) to enable stance detection in a generalized (non-domain, non-statement specific) form. Specifically, we test a variety of different general prompt chains for zero-shot stance classifications. Our evaluation data consists of textual data from a real-world empirical research project in the domain of sustainable urban transport. For 1710 German newspaper paragraphs, each containing an organizational entity, we annotated the stance of the entity toward one of five normative statements. A comparison of four publicly available LLMs show that they can achieve adequate performance. However, results heavily depend on the prompt chain method, LLM, and vary by statement. Our findings have implications for computational linguistics methodology and political discourse analysis, as they offer a deeper understanding of the strengths and weaknesses of LLMs in performing the complex semantic task of stance detection. We strongly emphasise the necessity of domain-specific evaluation data for evaluating LLMs, considering trade-offs between model complexity and performance, as well as honestly weighing drawbacks of LLM application against traditional, valid approaches, such as manually annotating representative text samples.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- University of Zürich, Zürich, Switzerland.
ORCID-Profile: Viviane Walker, Mario Angst
Förderung
- Digitalisierungsinitiative der Zürcher Hochschulen
Zitieren
APA
Walker, V., & Angst, M. (2025). Promises and pitfalls of using LLMs to identify actor stances in political discourse. PLOS One. https://doi.org/10.1371/journal.pone.0335547
Vancouver
Walker V, Angst M. Promises and pitfalls of using LLMs to identify actor stances in political discourse. PLOS One. 2025. doi:10.1371/journal.pone.0335547
BibTeX
@article{Walker2025,
author = {Walker, Viviane and Angst, Mario},
title = {Promises and pitfalls of using LLMs to identify actor stances in political discourse},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0335547}
}
EUVIMED