AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments

Till Raphael Saenger, Musashi Hinck, Justin Grimmer, Brandon M. Stewart


Abstract
We introduce a three-part framework for constructing persuasive messages, AutoPersuade. First, we curate a large collection of arguments and gather human evaluations of their persuasiveness. Next, we introduce a novel topic model to identify the features of these arguments that influence persuasion. Finally, we use the model to predict the persuasiveness of new arguments and to assess the causal effects of argument components, offering an explanation of the results. We demonstrate the effectiveness of AutoPersuade in an experimental study on arguments for veganism, validating our findings through human studies and out-of-sample predictions.
Anthology ID:
2024.emnlp-main.913
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16325–16342
Language:
URL:
https://aclanthology.org/2024.emnlp-main.913
DOI:
10.18653/v1/2024.emnlp-main.913
Bibkey:
Cite (ACL):
Till Raphael Saenger, Musashi Hinck, Justin Grimmer, and Brandon M. Stewart. 2024. AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 16325–16342, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments (Saenger et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.913.pdf
Data:
 2024.emnlp-main.913.data.zip