@inproceedings{saenger-etal-2024-autopersuade,
title = "{A}uto{P}ersuade: A Framework for Evaluating and Explaining Persuasive Arguments",
author = "Saenger, Till Raphael and
Hinck, Musashi and
Grimmer, Justin and
Stewart, Brandon M.",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.913",
doi = "10.18653/v1/2024.emnlp-main.913",
pages = "16325--16342",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saenger-etal-2024-autopersuade">
<titleInfo>
<title>AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments</title>
</titleInfo>
<name type="personal">
<namePart type="given">Till</namePart>
<namePart type="given">Raphael</namePart>
<namePart type="family">Saenger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Musashi</namePart>
<namePart type="family">Hinck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Grimmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brandon</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Stewart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">saenger-etal-2024-autopersuade</identifier>
<identifier type="doi">10.18653/v1/2024.emnlp-main.913</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.913</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>16325</start>
<end>16342</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments
%A Saenger, Till Raphael
%A Hinck, Musashi
%A Grimmer, Justin
%A Stewart, Brandon M.
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F saenger-etal-2024-autopersuade
%X 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.
%R 10.18653/v1/2024.emnlp-main.913
%U https://aclanthology.org/2024.emnlp-main.913
%U https://doi.org/10.18653/v1/2024.emnlp-main.913
%P 16325-16342
Markdown (Informal)
[AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments](https://aclanthology.org/2024.emnlp-main.913) (Saenger et al., EMNLP 2024)
ACL