EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

How to train your stochastic parrot: large language models for political texts

Joseph T. Ornstein, Elise N. Blasingame, Jake S. Truscott

Political Science Research and Methods · 2025-04 · 13 (2) · 264-281

DOI: 10.1017/psrm.2024.64 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Political Science Research and Methods, online erschienen am 14.01.2025. Verfasst von Joseph T. Ornstein und 2 weiteren Autor:innen. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We demonstrate how few-shot prompts to large language models (LLMs) can be effectively applied to a wide range of text-as-data tasks in political science—including sentiment analysis, document scaling, and topic modeling. In a series of pre-registered analyses, this approach outperforms conventional supervised learning methods without the need for extensive data pre-processing or large sets of labeled training data. Performance is comparable to expert and crowd-coding methods at a fraction of the cost. We propose a set of best practices for adapting these models to social science measurement tasks, and develop an open-source software package for researchers.

Zitieren

APA

Ornstein, J. T., Blasingame, E. N., & Truscott, J. S. (2025). How to train your stochastic parrot: large language models for political texts. Political Science Research and Methods, 13(2), 264-281. https://doi.org/10.1017/psrm.2024.64

Vancouver

Ornstein JT, Blasingame EN, Truscott JS. How to train your stochastic parrot: large language models for political texts. Political Science Research and Methods. 2025;13(2):264-281. doi:10.1017/psrm.2024.64

BibTeX
@article{Ornstein2025,
  author = {Ornstein, Joseph T. and Blasingame, Elise N. and Truscott, Jake S.},
  title = {How to train your stochastic parrot: large language models for political texts},
  journal = {Political Science Research and Methods},
  year = {2025},
  volume = {13},
  number = {2},
  pages = {264--281},
  doi = {10.1017/psrm.2024.64}
}
Kostenlos starten →