We introduce AutoPersuade, a three-part framework for constructing persuasive messages. First, we curate a large dataset of arguments with human evaluations. Next, we develop a novel topic model to identify argument features that influence persuasiveness. Finally, we use this model to predict the effectiveness of new arguments and assess the causal impact of different components to provide explanations. We validate AutoPersuade through an experimental study on arguments for veganism, demonstrating its effectiveness with human studies and out-of-sample predictions.
View on arXiv@article{saenger2025_2410.08917,
title={ AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments },
author={ Till Raphael Saenger and Musashi Hinck and Justin Grimmer and Brandon M. Stewart },
journal={arXiv preprint arXiv:2410.08917},
year={ 2025 }
}