AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929753899925504 |
|---|---|
| author | Saenger, Till Raphael Hinck, Musashi Grimmer, Justin Stewart, Brandon M. |
| author_facet | Saenger, Till Raphael Hinck, Musashi Grimmer, Justin Stewart, Brandon M. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08917 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments Saenger, Till Raphael Hinck, Musashi Grimmer, Justin Stewart, Brandon M. Computation and Language 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. |
| title | AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.08917 |