@inproceedings{sachdeva-etal-2022-targeted,
title = "Targeted Identity Group Prediction in Hate Speech Corpora",
author = "Sachdeva, Pratik and
Barreto, Renata and
Von Vacano, Claudia and
Kennedy, Chris",
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-1.22",
doi = "10.18653/v1/2022.woah-1.22",
pages = "231--244",
abstract = "The past decade has seen an abundance of work seeking to detect, characterize, and measure online hate speech. A related, but less studied problem, is the detection of identity groups targeted by that hate speech. Predictive accuracy on this task can supplement additional analyses beyond hate speech detection, motivating its study. Using the Measuring Hate Speech corpus, which provided annotations for targeted identity groups, we created neural network models to perform multi-label binary prediction of identity groups targeted by a comment. Specifically, we studied 8 broad identity groups and 12 identity sub-groups within race and gender identity. We found that these networks exhibited good predictive performance, achieving ROC AUCs of greater than 0.9 and PR AUCs of greater than 0.7 on several identity groups. We validated their performance on HateCheck and Gab Hate Corpora, finding that predictive performance generalized in most settings. We additionally examined the performance of the model on comments targeting multiple identity groups. Our results demonstrate the feasibility of simultaneously identifying targeted groups in social media comments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sachdeva-etal-2022-targeted">
<titleInfo>
<title>Targeted Identity Group Prediction in Hate Speech Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pratik</namePart>
<namePart type="family">Sachdeva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renata</namePart>
<namePart type="family">Barreto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Von Vacano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Kennedy</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>The past decade has seen an abundance of work seeking to detect, characterize, and measure online hate speech. A related, but less studied problem, is the detection of identity groups targeted by that hate speech. Predictive accuracy on this task can supplement additional analyses beyond hate speech detection, motivating its study. Using the Measuring Hate Speech corpus, which provided annotations for targeted identity groups, we created neural network models to perform multi-label binary prediction of identity groups targeted by a comment. Specifically, we studied 8 broad identity groups and 12 identity sub-groups within race and gender identity. We found that these networks exhibited good predictive performance, achieving ROC AUCs of greater than 0.9 and PR AUCs of greater than 0.7 on several identity groups. We validated their performance on HateCheck and Gab Hate Corpora, finding that predictive performance generalized in most settings. We additionally examined the performance of the model on comments targeting multiple identity groups. Our results demonstrate the feasibility of simultaneously identifying targeted groups in social media comments.</abstract>
<identifier type="citekey">sachdeva-etal-2022-targeted</identifier>
<identifier type="doi">10.18653/v1/2022.woah-1.22</identifier>
<location>
<url>https://aclanthology.org/2022.woah-1.22</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>231</start>
<end>244</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Targeted Identity Group Prediction in Hate Speech Corpora
%A Sachdeva, Pratik
%A Barreto, Renata
%A Von Vacano, Claudia
%A Kennedy, Chris
%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 sachdeva-etal-2022-targeted
%X The past decade has seen an abundance of work seeking to detect, characterize, and measure online hate speech. A related, but less studied problem, is the detection of identity groups targeted by that hate speech. Predictive accuracy on this task can supplement additional analyses beyond hate speech detection, motivating its study. Using the Measuring Hate Speech corpus, which provided annotations for targeted identity groups, we created neural network models to perform multi-label binary prediction of identity groups targeted by a comment. Specifically, we studied 8 broad identity groups and 12 identity sub-groups within race and gender identity. We found that these networks exhibited good predictive performance, achieving ROC AUCs of greater than 0.9 and PR AUCs of greater than 0.7 on several identity groups. We validated their performance on HateCheck and Gab Hate Corpora, finding that predictive performance generalized in most settings. We additionally examined the performance of the model on comments targeting multiple identity groups. Our results demonstrate the feasibility of simultaneously identifying targeted groups in social media comments.
%R 10.18653/v1/2022.woah-1.22
%U https://aclanthology.org/2022.woah-1.22
%U https://doi.org/10.18653/v1/2022.woah-1.22
%P 231-244
Markdown (Informal)
[Targeted Identity Group Prediction in Hate Speech Corpora](https://aclanthology.org/2022.woah-1.22) (Sachdeva et al., WOAH 2022)
ACL
- Pratik Sachdeva, Renata Barreto, Claudia Von Vacano, and Chris Kennedy. 2022. Targeted Identity Group Prediction in Hate Speech Corpora. In Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH), pages 231–244, Seattle, Washington (Hybrid). Association for Computational Linguistics.