CoChat

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

Ornstein, Joseph T., Blasingame, Elise N., Truscott, Jake S. · 2025 · Political Science Research and Methods
Cited by 44

The DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.

Abstract

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.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1017/psrm.2024.64

Cites

18 of 18 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 18 references

Research works printed but not linked: 23

  1. Le Mens, G and Gallego, A (2023) Scaling Political Texts with ChatGPT. arXiv:2311.16639. · arXiv
  2. 10.1146/annurev-polisci-051120-111443 · DOI
  3. 10.1017/S0003055416000058 · DOI · Paper page
  4. Widmann, 2022, Creating and comparing dictionary, word embedding, and transformer-based models to measure discrete emotions in German political text, Political Analysis, 31, 1
  5. 10.1146/annurev-polisci-053119-015921 · DOI · Paper page
  6. 10.1111/ajps.12779 · DOI
  7. Ying, 2021, Topics, concepts, and measurement: a crowdsourced procedure for validating topics as measures, Political Analysis, 30, 1
  8. Firth, J (ed) (1957) Studies in Linguistic Analysis. Special Volume of the Philological Society. Blackwell, Oxford, repr edition.
  9. 10.2139/ssrn.4389233 · DOI · Paper page
  10. 10.1017/9781108769495 · DOI
  11. 10.1017/pan.2019.32 · DOI
  12. 10.1111/j.1939-9162.2010.00006.x · DOI · Paper page
  13. 10.1111/ajps.12423 · DOI
  14. 10.1086/715162 · DOI · Paper page
  15. 10.1038/s42256-021-00359-2 · DOI
  16. 10.1017/S0003055417000302 · DOI
  17. Blei, 2003, Latent Dirichlet allocation, Journal of Machine Learning Research, 3, 993
  18. Vaswani, A , Shazeer, N , Parmar, N , Uszkoreit, J , Jones, L , Gomez, AN , Kaiser, L and Polosukhin, I (2017) Attention is all you need. arXiv:1706.03762 [cs]. · arXiv
  19. Grimmer, 2022, Text as Data: A New Framework for Machine Learning and the Social Sciences
  20. Go, 2009, Twitter sentiment classification using distant supervision, CS224N Project Report, Stanford, 1, 1
  21. 10.1609/aimag.v41i4.5304 · DOI
  22. Surowiecki, 2004, The Wisdom of Crowds: Why the Many are Smarter than the Few and How Collective Wisdom Shapes Business, Economies, Societies and Nations
  23. 10.1017/pan.2017.39 · DOI · Paper page

Cited by

Metadata

Authors
Ornstein, J. T., Blasingame, E. N., & Truscott, J. S.
Venue
Political Science Research and Methods
Published
2025-01-14
Volume
13
Issue
2
Pages
264-281
ISSN
  • 2049-8470
  • 2049-8489
Cited by
44
References
18
Language
en

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.