Journal article · 2025 · Open access
Comparing the persuasiveness of role-playing large language models and human experts on polarized U.S. political issues
AI & Society, 41(1), 351–361 · Published 16 July 2025 · DOI 10.1007/s00146-025-02464-x
In brief
“Comparing the persuasiveness of role-playing large language models and human experts on polarized U.S. political issues” is a 2025 journal article by Kobi Hackenburg and 3 co-authors, published in AI & Society. OpenAlex counts 65 citations as of 22 November 2026, which puts it in the top 2% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at AI & Society.
- Citations
- 65
- Most cited in
- 2026 (32)
- Field-weighted impact
- 42.29
- References
- 41
- Authors
- 4
Abstract
Advances in large language models (LLMs) could significantly disrupt political communication. In a large-scale pre-registered experiment ( n = 4955), we prompted GPT-4 to generate persuasive messages impersonating the language and beliefs of U.S. political parties—a technique we term “partisan role-play”—and directly compared their persuasiveness to that of human persuasion experts. In aggregate, the persuasive impact of role-playing messages generated by GPT-4 was not significantly different from that of non-role-playing messages. However, the persuasive impact of GPT-4 rivaled, and on some issues exceeded, that of the human experts. Taken together, our findings suggest that — contrary to popular concern — instructing current LLMs to role-play as partisans offers limited persuasive advantage, but also that current LLMs can rival and even exceed the persuasiveness of human experts. These results potentially portend widespread adoption of AI tools by persuasion campaigns, with important implications for the role of AI in politics and democracy.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Hackenburg, K., Ibrahim, L., Tappin, B. M., & Tsakiris, M. (2025). Comparing the persuasiveness of role-playing large language models and human experts on polarized U.S. political issues. AI & Society, 41(1), 351–361. https://doi.org/10.1007/s00146-025-02464-x
MLA 9
Hackenburg, Kobi, et al. “Comparing the persuasiveness of role-playing large language models and human experts on polarized U.S. political issues.” AI & Society, vol. 41, no. 1, 2025, pp. 351–361. https://doi.org/10.1007/s00146-025-02464-x.
Chicago
Hackenburg, Kobi, Lujain Ibrahim, Ben M Tappin, and Manos Tsakiris. 2025. “Comparing the persuasiveness of role-playing large language models and human experts on polarized U.S. political issues.” AI & Society 41 (1): 351–361. https://doi.org/10.1007/s00146-025-02464-x.
Harvard
Hackenburg, K. et al. (2025) ‘Comparing the persuasiveness of role-playing large language models and human experts on polarized U.S. political issues’, AI & Society, 41(1), pp. 351–361. doi:10.1007/s00146-025-02464-x.
IEEE
K. Hackenburg, L. Ibrahim, B. M. Tappin, and M. Tsakiris, “Comparing the persuasiveness of role-playing large language models and human experts on polarized U.S. political issues,” AI & Society, vol. 41, no. 1, pp. 351–361, 2025, doi: 10.1007/s00146-025-02464-x.
BibTeX
@article{hackenburg2025comparing,
title = {{Comparing the persuasiveness of role-playing large language models and human experts on polarized U.S. political issues}},
author = {Hackenburg, Kobi and Ibrahim, Lujain and Tappin, Ben M and Tsakiris, Manos},
journal = {AI \& Society},
year = {2025},
volume = {41},
number = {1},
pages = {351--361},
doi = {10.1007/s00146-025-02464-x},
url = {https://doi.org/10.1007/s00146-025-02464-x}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 7 | |
| 2025 | 26 | |
| 2026 | 32 |
Its field-weighted citation impact is 42.29: it has been cited 42.29 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Social Sciences › Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
- large language models
- GPT-4
- role play
- persuasion
- political polarization
- political communication
- political parties
Work with this paper
Most-cited papers in Social Sciences
- Using thematic analysis in psychologyVirginia Braun, Victoria Clarke · Qualitative Research in Psychology · 2006 · 240,222 citations
- Case Study Research: Design and MethodsRobert K. Yin · 1984 · 81,951 citations
- Three Approaches to Qualitative Content AnalysisHsiu-Fang Hsieh, Sarah Elizabeth Shannon · Qualitative Health Research · 2005 · 49,623 citations
- Qualitative Data Analysis: An Expanded SourcebookMatthew B. Miles, A Michael Huberman · Journal of Environmental Psychology · 1994 · 48,311 citations
- Consolidated criteria for reporting qualitative research (COREQ): a 32-item checklist for interviews and focus groupsAllison Tong, Peter Sainsbury, Jonathan C. Craig · International Journal for Quality in Health Care · 2007 · 45,353 citations
Questions about this paper
How do I cite this paper in APA style?
Hackenburg, K., Ibrahim, L., Tappin, B. M., & Tsakiris, M. (2025). Comparing the persuasiveness of role-playing large language models and human experts on polarized U.S. political issues. AI & Society, 41(1), 351–361. https://doi.org/10.1007/s00146-025-02464-x
How many times has this paper been cited?
65 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at AI & Society: sign in and open the PDF from this page.
Who wrote this paper?
Kobi Hackenburg, Lujain Ibrahim, Ben M Tappin, Manos Tsakiris.
What is the DOI of this paper?
10.1007/s00146-025-02464-x, permanently at https://doi.org/10.1007/s00146-025-02464-x. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.