@inproceedings{ashida-komachi-2022-towards,
title = "Towards Automatic Generation of Messages Countering Online Hate Speech and Microaggressions",
author = "Ashida, Mana and
Komachi, Mamoru",
editor = "Narang, Kanika and
Mostafazadeh Davani, Aida and
Mathias, Lambert and
Vidgen, Bertie and
Talat, Zeerak",
booktitle = "Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)",
month = jul,
year = "2022",
address = "Seattle, Washington (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.woah-1.2/",
doi = "10.18653/v1/2022.woah-1.2",
pages = "11--23",
abstract = "With the widespread use of social media, online hate is increasing, and microaggressions are receiving attention. We explore the potential for using pretrained language models to automatically generate messages that combat the associated offensive texts. Specifically, we focus on using prompting to steer model generation as it requires less data and computation than fine-tuning. We also propose a human evaluation perspective; offensiveness, stance, and informativeness. After obtaining 306 counterspeech and 42 microintervention messages generated by GPT-2, 3, Neo, we conducted a human evaluation using Amazon Mechanical Turk. The results indicate the potential of using prompting in the proposed generation task. All the generated texts along with the annotation are published to encourage future research on countering hate and microaggressions online."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ashida-komachi-2022-towards">
<titleInfo>
<title>Towards Automatic Generation of Messages Countering Online Hate Speech and Microaggressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mana</namePart>
<namePart type="family">Ashida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kanika</namePart>
<namePart type="family">Narang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Mostafazadeh Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lambert</namePart>
<namePart type="family">Mathias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bertie</namePart>
<namePart type="family">Vidgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Talat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, Washington (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the widespread use of social media, online hate is increasing, and microaggressions are receiving attention. We explore the potential for using pretrained language models to automatically generate messages that combat the associated offensive texts. Specifically, we focus on using prompting to steer model generation as it requires less data and computation than fine-tuning. We also propose a human evaluation perspective; offensiveness, stance, and informativeness. After obtaining 306 counterspeech and 42 microintervention messages generated by GPT-2, 3, Neo, we conducted a human evaluation using Amazon Mechanical Turk. The results indicate the potential of using prompting in the proposed generation task. All the generated texts along with the annotation are published to encourage future research on countering hate and microaggressions online.</abstract>
<identifier type="citekey">ashida-komachi-2022-towards</identifier>
<identifier type="doi">10.18653/v1/2022.woah-1.2</identifier>
<location>
<url>https://aclanthology.org/2022.woah-1.2/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>11</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Automatic Generation of Messages Countering Online Hate Speech and Microaggressions
%A Ashida, Mana
%A Komachi, Mamoru
%Y Narang, Kanika
%Y Mostafazadeh Davani, Aida
%Y Mathias, Lambert
%Y Vidgen, Bertie
%Y Talat, Zeerak
%S Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, Washington (Hybrid)
%F ashida-komachi-2022-towards
%X With the widespread use of social media, online hate is increasing, and microaggressions are receiving attention. We explore the potential for using pretrained language models to automatically generate messages that combat the associated offensive texts. Specifically, we focus on using prompting to steer model generation as it requires less data and computation than fine-tuning. We also propose a human evaluation perspective; offensiveness, stance, and informativeness. After obtaining 306 counterspeech and 42 microintervention messages generated by GPT-2, 3, Neo, we conducted a human evaluation using Amazon Mechanical Turk. The results indicate the potential of using prompting in the proposed generation task. All the generated texts along with the annotation are published to encourage future research on countering hate and microaggressions online.
%R 10.18653/v1/2022.woah-1.2
%U https://aclanthology.org/2022.woah-1.2/
%U https://doi.org/10.18653/v1/2022.woah-1.2
%P 11-23
Markdown (Informal)
[Towards Automatic Generation of Messages Countering Online Hate Speech and Microaggressions](https://aclanthology.org/2022.woah-1.2/) (Ashida & Komachi, WOAH 2022)
ACL