Evaluating the persuasive influence of political microtargeting with large language models
Proceedings of the National Academy of Sciences · 11.06.2024 · 121 (24)
DOI: 10.1073/pnas.2403116121 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 07.06.2024. Verfasst von Kobi Hackenburg und 1 weiteren Autor:innen. Beteiligte Einrichtung: Oxford Internet Institute, University of Oxford, Oxford OX1 2JD, United Kingdom. Hauptthemen laut MEDLINE: Politics, Persuasive Communication. Die Arbeit wurde bisher 119-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Recent advancements in large language models (LLMs) have raised the prospect of scalable, automated, and fine-grained political microtargeting on a scale previously unseen; however, the persuasive influence of microtargeting with LLMs remains unclear. Here, we build a custom web application capable of integrating self-reported demographic and political data into GPT-4 prompts in real-time, facilitating the live creation of unique messages tailored to persuade individual users on four political issues. We then deploy this application in a preregistered randomized control experiment ( n = 8,587) to investigate the extent to which access to individual-level data increases the persuasive influence of GPT-4. Our approach yields two key findings. First, messages generated by GPT-4 were broadly persuasive, in some cases increasing support for an issue stance by up to 12 percentage points. Second, in aggregate, the persuasive impact of microtargeted messages was not statistically different from that of non-microtargeted messages (4.83 vs. 6.20 percentage points, respectively, P = 0.226). These trends hold even when manipulating the type and number of attributes used to tailor the message. These findings suggest—contrary to widespread speculation—that the influence of current LLMs may reside not in their ability to tailor messages to individuals but rather in the persuasiveness of their generic, nontargeted messages. We release our experimental dataset, GPTarget2024 , as an empirical baseline for future research.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Oxford Internet Institute, University of Oxford, Oxford OX1 2JD, United Kingdom.
ORCID-Profile: Kobi Hackenburg, Helen Margetts
Zitieren
APA
Hackenburg, K., & Margetts, H. (2024). Evaluating the persuasive influence of political microtargeting with large language models. Proceedings of the National Academy of Sciences, 121(24). https://doi.org/10.1073/pnas.2403116121
Vancouver
Hackenburg K, Margetts H. Evaluating the persuasive influence of political microtargeting with large language models. Proceedings of the National Academy of Sciences. 2024;121(24). doi:10.1073/pnas.2403116121
BibTeX
@article{Hackenburg2024,
author = {Hackenburg, Kobi and Margetts, Helen},
title = {Evaluating the persuasive influence of political microtargeting with large language models},
journal = {Proceedings of the National Academy of Sciences},
year = {2024},
volume = {121},
number = {24},
doi = {10.1073/pnas.2403116121}
}
EUVIMED