@inproceedings{lees-etal-2021-capturing,
title = "Capturing Covertly Toxic Speech via Crowdsourcing",
author = "Lees, Alyssa and
Borkan, Daniel and
Kivlichan, Ian and
Nario, Jorge and
Goyal, Tesh",
editor = "Blodgett, Su Lin and
Madaio, Michael and
O'Connor, Brendan and
Wallach, Hanna and
Yang, Qian",
booktitle = "Proceedings of the First Workshop on Bridging Human{--}Computer Interaction and Natural Language Processing",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.hcinlp-1.3",
pages = "14--20",
abstract = "We study the task of labeling covert or veiled toxicity in online conversations. Prior research has highlighted the difficulty in creating language models that recognize nuanced toxicity such as microaggressions. Our investigations further underscore the difficulty in parsing such labels reliably from raters via crowdsourcing. We introduce an initial dataset, COVERTTOXICITY, which aims to identify and categorize such comments from a refined rater template. Finally, we fine-tune a comment-domain BERT model to classify covertly offensive comments and compare against existing baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lees-etal-2021-capturing">
<titleInfo>
<title>Capturing Covertly Toxic Speech via Crowdsourcing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alyssa</namePart>
<namePart type="family">Lees</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Borkan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ian</namePart>
<namePart type="family">Kivlichan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Nario</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tesh</namePart>
<namePart type="family">Goyal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Su</namePart>
<namePart type="given">Lin</namePart>
<namePart type="family">Blodgett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Madaio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brendan</namePart>
<namePart type="family">O’Connor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="family">Wallach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We study the task of labeling covert or veiled toxicity in online conversations. Prior research has highlighted the difficulty in creating language models that recognize nuanced toxicity such as microaggressions. Our investigations further underscore the difficulty in parsing such labels reliably from raters via crowdsourcing. We introduce an initial dataset, COVERTTOXICITY, which aims to identify and categorize such comments from a refined rater template. Finally, we fine-tune a comment-domain BERT model to classify covertly offensive comments and compare against existing baselines.</abstract>
<identifier type="citekey">lees-etal-2021-capturing</identifier>
<location>
<url>https://aclanthology.org/2021.hcinlp-1.3</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>14</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Capturing Covertly Toxic Speech via Crowdsourcing
%A Lees, Alyssa
%A Borkan, Daniel
%A Kivlichan, Ian
%A Nario, Jorge
%A Goyal, Tesh
%Y Blodgett, Su Lin
%Y Madaio, Michael
%Y O’Connor, Brendan
%Y Wallach, Hanna
%Y Yang, Qian
%S Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F lees-etal-2021-capturing
%X We study the task of labeling covert or veiled toxicity in online conversations. Prior research has highlighted the difficulty in creating language models that recognize nuanced toxicity such as microaggressions. Our investigations further underscore the difficulty in parsing such labels reliably from raters via crowdsourcing. We introduce an initial dataset, COVERTTOXICITY, which aims to identify and categorize such comments from a refined rater template. Finally, we fine-tune a comment-domain BERT model to classify covertly offensive comments and compare against existing baselines.
%U https://aclanthology.org/2021.hcinlp-1.3
%P 14-20
Markdown (Informal)
[Capturing Covertly Toxic Speech via Crowdsourcing](https://aclanthology.org/2021.hcinlp-1.3) (Lees et al., HCINLP 2021)
ACL
- Alyssa Lees, Daniel Borkan, Ian Kivlichan, Jorge Nario, and Tesh Goyal. 2021. Capturing Covertly Toxic Speech via Crowdsourcing. In Proceedings of the First Workshop on Bridging Human–Computer Interaction and Natural Language Processing, pages 14–20, Online. Association for Computational Linguistics.