Project repository for "Evaluating the persuasive influence of political microtargeting with large language models" by Kobi Hackenburg and Helen Margetts. Code for the web application can be made available for replication or research efforts upon request.
In June 2024 this article was published in PNAS. You can cite our work using the following bibtex entry:
@article{Hackenburg2024,
abstract = {SignificanceAdvances in large language models (LLMs) have raised concerns over scalable, personalized political persuasion. Here, we integrate user data into GPT-4 prompts in real-time, facilitatin...},
author = {Kobi Hackenburg and Helen Margetts},
doi = {10.1073/PNAS.2403116121},
issn = {0027-8424},
issue = {24},
journal = {Proceedings of the National Academy of Sciences},
keywords = {AI safety,AI-mediated communication,large language models,microtargeting,political persuasion},
month = {6},
pages = {e2403116121},
publisher = {National Academy of Sciences},
title = {Evaluating the persuasive influence of political microtargeting with large language models},
volume = {121},
url = {https://www.pnas.org/doi/abs/10.1073/pnas.2403116121},
year = {2024},
}