@inproceedings{sougata-rohini-2023-consolidating,
title = "Consolidating Strategies for Countering Hate Speech Using Persuasive Dialogues",
author = "Sougata, Saha and
Rohini, Srihari",
editor = "Jyoti, D. Pawar and
Sobha, Lalitha Devi",
booktitle = "Proceedings of the 20th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2023",
address = "Goa University, Goa, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2023.icon-1.30",
pages = "378--392",
abstract = "Hateful comments are prevalent on social media platforms. Although tools for automatically detecting, flagging, and blocking such false, offensive, and harmful content online have lately matured, such reactive and brute force methods alone provide short-term and superficial remedies while the perpetrators persist. With the public availability of large language models which can generate articulate synthetic and engaging content at scale, there are concerns about the rapid growth of dissemination of such malicious content on the web. There is now a need to focus on deeper, long-term solutions that involve engaging with the human perpetrator behind the source of the content to change their viewpoint or at least bring down the rhetoric using persuasive means. To do that, we propose defining and experimenting with controllable strategies for generating counterarguments to hateful comments in online conversations. We experiment with controlling response generation using features based on (i) argument structure and reasoning-based Walton argument schemes, (ii) counter-argument speech acts, and (iii) human characteristicsbased qualities such as Big-5 personality traits and human values. Using automatic and human evaluations, we determine the best combination of features that generate fluent, argumentative, and logically sound arguments for countering hate. We further share the developed computational models for automatically annotating text with such features, and a silver-standard annotated version of an existing hate speech dialog corpora.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sougata-rohini-2023-consolidating">
<titleInfo>
<title>Consolidating Strategies for Countering Hate Speech Using Persuasive Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saha</namePart>
<namePart type="family">Sougata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srihari</namePart>
<namePart type="family">Rohini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">D</namePart>
<namePart type="given">Pawar</namePart>
<namePart type="family">Jyoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lalitha</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Sobha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Goa University, Goa, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hateful comments are prevalent on social media platforms. Although tools for automatically detecting, flagging, and blocking such false, offensive, and harmful content online have lately matured, such reactive and brute force methods alone provide short-term and superficial remedies while the perpetrators persist. With the public availability of large language models which can generate articulate synthetic and engaging content at scale, there are concerns about the rapid growth of dissemination of such malicious content on the web. There is now a need to focus on deeper, long-term solutions that involve engaging with the human perpetrator behind the source of the content to change their viewpoint or at least bring down the rhetoric using persuasive means. To do that, we propose defining and experimenting with controllable strategies for generating counterarguments to hateful comments in online conversations. We experiment with controlling response generation using features based on (i) argument structure and reasoning-based Walton argument schemes, (ii) counter-argument speech acts, and (iii) human characteristicsbased qualities such as Big-5 personality traits and human values. Using automatic and human evaluations, we determine the best combination of features that generate fluent, argumentative, and logically sound arguments for countering hate. We further share the developed computational models for automatically annotating text with such features, and a silver-standard annotated version of an existing hate speech dialog corpora.</abstract>
<identifier type="citekey">sougata-rohini-2023-consolidating</identifier>
<location>
<url>https://aclanthology.org/2023.icon-1.30</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>378</start>
<end>392</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Consolidating Strategies for Countering Hate Speech Using Persuasive Dialogues
%A Sougata, Saha
%A Rohini, Srihari
%Y Jyoti, D. Pawar
%Y Sobha, Lalitha Devi
%S Proceedings of the 20th International Conference on Natural Language Processing (ICON)
%D 2023
%8 December
%I NLP Association of India (NLPAI)
%C Goa University, Goa, India
%F sougata-rohini-2023-consolidating
%X Hateful comments are prevalent on social media platforms. Although tools for automatically detecting, flagging, and blocking such false, offensive, and harmful content online have lately matured, such reactive and brute force methods alone provide short-term and superficial remedies while the perpetrators persist. With the public availability of large language models which can generate articulate synthetic and engaging content at scale, there are concerns about the rapid growth of dissemination of such malicious content on the web. There is now a need to focus on deeper, long-term solutions that involve engaging with the human perpetrator behind the source of the content to change their viewpoint or at least bring down the rhetoric using persuasive means. To do that, we propose defining and experimenting with controllable strategies for generating counterarguments to hateful comments in online conversations. We experiment with controlling response generation using features based on (i) argument structure and reasoning-based Walton argument schemes, (ii) counter-argument speech acts, and (iii) human characteristicsbased qualities such as Big-5 personality traits and human values. Using automatic and human evaluations, we determine the best combination of features that generate fluent, argumentative, and logically sound arguments for countering hate. We further share the developed computational models for automatically annotating text with such features, and a silver-standard annotated version of an existing hate speech dialog corpora.
%U https://aclanthology.org/2023.icon-1.30
%P 378-392
Markdown (Informal)
[Consolidating Strategies for Countering Hate Speech Using Persuasive Dialogues](https://aclanthology.org/2023.icon-1.30) (Sougata & Rohini, ICON 2023)
ACL