@inproceedings{zheng-etal-2024-hatemoderate,
title = "{H}ate{M}oderate: Testing Hate Speech Detectors against Content Moderation Policies",
author = "Zheng, Jiangrui and
Liu, Xueqing and
Haque, Mirazul and
Qian, Xing and
Yang, Guanqun and
Yang, Wei",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.172/",
doi = "10.18653/v1/2024.findings-naacl.172",
pages = "2691--2710",
abstract = "To protect users from massive hateful content, existing works studied automated hate speech detection. Despite the existing efforts, one question remains: Do automated hate speech detectors conform to social media content policies? A platform`s content policies are a checklist of content moderated by the social media platform. Because content moderation rules are often uniquely defined, existing hate speech datasets cannot directly answer this question. This work seeks to answer this question by creating HateModerate, a dataset for testing the behaviors of automated content moderators against content policies. First, we engage 28 annotators and GPT in a six-step annotation process, resulting in a list of hateful and non-hateful test suites matching each of Facebook`s 41 hate speech policies. Second, we test the performance of state-of-the-art hate speech detectors against HateModerate, revealing substantial failures these models have in their conformity to the policies. Third, using HateModerate, we augment the training data of a top-downloaded hate detector on HuggingFace. We observe significant improvement in the models' conformity to content policies while having comparable scores on the original test data. Our dataset and code can be found on https://github.com/stevens-textmining/HateModerate."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2024-hatemoderate">
<titleInfo>
<title>HateModerate: Testing Hate Speech Detectors against Content Moderation Policies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiangrui</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xueqing</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mirazul</namePart>
<namePart type="family">Haque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guanqun</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To protect users from massive hateful content, existing works studied automated hate speech detection. Despite the existing efforts, one question remains: Do automated hate speech detectors conform to social media content policies? A platform‘s content policies are a checklist of content moderated by the social media platform. Because content moderation rules are often uniquely defined, existing hate speech datasets cannot directly answer this question. This work seeks to answer this question by creating HateModerate, a dataset for testing the behaviors of automated content moderators against content policies. First, we engage 28 annotators and GPT in a six-step annotation process, resulting in a list of hateful and non-hateful test suites matching each of Facebook‘s 41 hate speech policies. Second, we test the performance of state-of-the-art hate speech detectors against HateModerate, revealing substantial failures these models have in their conformity to the policies. Third, using HateModerate, we augment the training data of a top-downloaded hate detector on HuggingFace. We observe significant improvement in the models’ conformity to content policies while having comparable scores on the original test data. Our dataset and code can be found on https://github.com/stevens-textmining/HateModerate.</abstract>
<identifier type="citekey">zheng-etal-2024-hatemoderate</identifier>
<identifier type="doi">10.18653/v1/2024.findings-naacl.172</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.172/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>2691</start>
<end>2710</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HateModerate: Testing Hate Speech Detectors against Content Moderation Policies
%A Zheng, Jiangrui
%A Liu, Xueqing
%A Haque, Mirazul
%A Qian, Xing
%A Yang, Guanqun
%A Yang, Wei
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zheng-etal-2024-hatemoderate
%X To protect users from massive hateful content, existing works studied automated hate speech detection. Despite the existing efforts, one question remains: Do automated hate speech detectors conform to social media content policies? A platform‘s content policies are a checklist of content moderated by the social media platform. Because content moderation rules are often uniquely defined, existing hate speech datasets cannot directly answer this question. This work seeks to answer this question by creating HateModerate, a dataset for testing the behaviors of automated content moderators against content policies. First, we engage 28 annotators and GPT in a six-step annotation process, resulting in a list of hateful and non-hateful test suites matching each of Facebook‘s 41 hate speech policies. Second, we test the performance of state-of-the-art hate speech detectors against HateModerate, revealing substantial failures these models have in their conformity to the policies. Third, using HateModerate, we augment the training data of a top-downloaded hate detector on HuggingFace. We observe significant improvement in the models’ conformity to content policies while having comparable scores on the original test data. Our dataset and code can be found on https://github.com/stevens-textmining/HateModerate.
%R 10.18653/v1/2024.findings-naacl.172
%U https://aclanthology.org/2024.findings-naacl.172/
%U https://doi.org/10.18653/v1/2024.findings-naacl.172
%P 2691-2710
Markdown (Informal)
[HateModerate: Testing Hate Speech Detectors against Content Moderation Policies](https://aclanthology.org/2024.findings-naacl.172/) (Zheng et al., Findings 2024)
ACL