@inproceedings{carvallo-etal-2025-hate,
title = "Hate Explained: Evaluating {NER}-Enriched Text in Human and Machine Moderation of Hate Speech",
author = "Carvallo, Andres and
Mendoza, Marcelo and
Fernandez, Miguel and
Ojeda, Maximiliano and
Guevara, Lilly and
Varela, Diego and
Borquez, Martin and
Buzeta, Nicolas and
Ayala, Felipe",
editor = "Calabrese, Agostina and
de Kock, Christine and
Nozza, Debora and
Plaza-del-Arco, Flor Miriam and
Talat, Zeerak and
Vargas, Francielle",
booktitle = "Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)",
month = aug,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.woah-1.42/",
pages = "458--467",
ISBN = "979-8-89176-105-6",
abstract = "Hate speech detection is vital for creating safe online environments, as harmful content can drive social polarization. This study explores the impact of enriching text with intent and group tags on machine performance and human moderation workflows. For machine performance, we enriched text with intent and group tags to train hate speech classifiers. Intent tags were the most effective, achieving state-of-the-art F1-score improvements on the IHC, SBIC, and DH datasets, respectively. Cross-dataset evaluations further demonstrated the superior generalization of intent-tagged models compared to other pre-trained approaches. Then, through a user study (N=100), we evaluated seven moderation settings, including intent tags, group tags, model probabilities, and randomized counterparts. Intent annotations significantly improved the accuracy of the moderators, allowing them to outperform machine classifiers by 12.9{\%}. Moderators also rated intent tags as the most useful explanation tool, with a 41{\%} increase in perceived helpfulness over the control group. Our findings demonstrate that intent-based annotations enhance both machine classification performance and human moderation workflows."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="carvallo-etal-2025-hate">
<titleInfo>
<title>Hate Explained: Evaluating NER-Enriched Text in Human and Machine Moderation of Hate Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andres</namePart>
<namePart type="family">Carvallo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcelo</namePart>
<namePart type="family">Mendoza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Fernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maximiliano</namePart>
<namePart type="family">Ojeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lilly</namePart>
<namePart type="family">Guevara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Varela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Borquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicolas</namePart>
<namePart type="family">Buzeta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felipe</namePart>
<namePart type="family">Ayala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agostina</namePart>
<namePart type="family">Calabrese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">de Kock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flor</namePart>
<namePart type="given">Miriam</namePart>
<namePart type="family">Plaza-del-Arco</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>
<name type="personal">
<namePart type="given">Francielle</namePart>
<namePart type="family">Vargas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-105-6</identifier>
</relatedItem>
<abstract>Hate speech detection is vital for creating safe online environments, as harmful content can drive social polarization. This study explores the impact of enriching text with intent and group tags on machine performance and human moderation workflows. For machine performance, we enriched text with intent and group tags to train hate speech classifiers. Intent tags were the most effective, achieving state-of-the-art F1-score improvements on the IHC, SBIC, and DH datasets, respectively. Cross-dataset evaluations further demonstrated the superior generalization of intent-tagged models compared to other pre-trained approaches. Then, through a user study (N=100), we evaluated seven moderation settings, including intent tags, group tags, model probabilities, and randomized counterparts. Intent annotations significantly improved the accuracy of the moderators, allowing them to outperform machine classifiers by 12.9%. Moderators also rated intent tags as the most useful explanation tool, with a 41% increase in perceived helpfulness over the control group. Our findings demonstrate that intent-based annotations enhance both machine classification performance and human moderation workflows.</abstract>
<identifier type="citekey">carvallo-etal-2025-hate</identifier>
<location>
<url>https://aclanthology.org/2025.woah-1.42/</url>
</location>
<part>
<date>2025-08</date>
<extent unit="page">
<start>458</start>
<end>467</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hate Explained: Evaluating NER-Enriched Text in Human and Machine Moderation of Hate Speech
%A Carvallo, Andres
%A Mendoza, Marcelo
%A Fernandez, Miguel
%A Ojeda, Maximiliano
%A Guevara, Lilly
%A Varela, Diego
%A Borquez, Martin
%A Buzeta, Nicolas
%A Ayala, Felipe
%Y Calabrese, Agostina
%Y de Kock, Christine
%Y Nozza, Debora
%Y Plaza-del-Arco, Flor Miriam
%Y Talat, Zeerak
%Y Vargas, Francielle
%S Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-105-6
%F carvallo-etal-2025-hate
%X Hate speech detection is vital for creating safe online environments, as harmful content can drive social polarization. This study explores the impact of enriching text with intent and group tags on machine performance and human moderation workflows. For machine performance, we enriched text with intent and group tags to train hate speech classifiers. Intent tags were the most effective, achieving state-of-the-art F1-score improvements on the IHC, SBIC, and DH datasets, respectively. Cross-dataset evaluations further demonstrated the superior generalization of intent-tagged models compared to other pre-trained approaches. Then, through a user study (N=100), we evaluated seven moderation settings, including intent tags, group tags, model probabilities, and randomized counterparts. Intent annotations significantly improved the accuracy of the moderators, allowing them to outperform machine classifiers by 12.9%. Moderators also rated intent tags as the most useful explanation tool, with a 41% increase in perceived helpfulness over the control group. Our findings demonstrate that intent-based annotations enhance both machine classification performance and human moderation workflows.
%U https://aclanthology.org/2025.woah-1.42/
%P 458-467
Markdown (Informal)
[Hate Explained: Evaluating NER-Enriched Text in Human and Machine Moderation of Hate Speech](https://aclanthology.org/2025.woah-1.42/) (Carvallo et al., WOAH 2025)
ACL
- Andres Carvallo, Marcelo Mendoza, Miguel Fernandez, Maximiliano Ojeda, Lilly Guevara, Diego Varela, Martin Borquez, Nicolas Buzeta, and Felipe Ayala. 2025. Hate Explained: Evaluating NER-Enriched Text in Human and Machine Moderation of Hate Speech. In Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH), pages 458–467, Vienna, Austria. Association for Computational Linguistics.