<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lopez-long-etal-2021-interaction">
    <titleInfo>
        <title>On the Interaction between Annotation Quality and Classifier Performance in Abusive Language Detection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Holly</namePart>
        <namePart type="family">Lopez Long</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexandra</namePart>
        <namePart type="family">O’Neil</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sandra</namePart>
        <namePart type="family">Kübler</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd.</publisher>
            <place>
                <placeTerm type="text">Held Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Abusive language detection has become an important tool for the cultivation of safe online platforms. We investigate the interaction of annotation quality and classifier performance. We use a new, fine-grained annotation scheme that allows us to distinguish between abusive language and colloquial uses of profanity that are not meant to harm. Our results show a tendency of crowd workers to overuse the abusive class, which creates an unrealistic class balance and affects classification accuracy. We also investigate different methods of distinguishing between explicit and implicit abuse and show lexicon-based approaches either over- or under-estimate the proportion of explicit abuse in data sets.</abstract>
    <identifier type="citekey">lopez-long-etal-2021-interaction</identifier>
    <location>
        <url>https://aclanthology.org/2021.ranlp-1.99</url>
    </location>
    <part>
        <date>2021-09</date>
        <extent unit="page">
            <start>868</start>
            <end>875</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T On the Interaction between Annotation Quality and Classifier Performance in Abusive Language Detection
%A Lopez Long, Holly
%A O’Neil, Alexandra
%A Kübler, Sandra
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
%D 2021
%8 September
%I INCOMA Ltd.
%C Held Online
%F lopez-long-etal-2021-interaction
%X Abusive language detection has become an important tool for the cultivation of safe online platforms. We investigate the interaction of annotation quality and classifier performance. We use a new, fine-grained annotation scheme that allows us to distinguish between abusive language and colloquial uses of profanity that are not meant to harm. Our results show a tendency of crowd workers to overuse the abusive class, which creates an unrealistic class balance and affects classification accuracy. We also investigate different methods of distinguishing between explicit and implicit abuse and show lexicon-based approaches either over- or under-estimate the proportion of explicit abuse in data sets.
%U https://aclanthology.org/2021.ranlp-1.99
%P 868-875

Markdown (Informal)

[On the Interaction between Annotation Quality and Classifier Performance in Abusive Language Detection](https://aclanthology.org/2021.ranlp-1.99) (Lopez Long et al., RANLP 2021)

• On the Interaction between Annotation Quality and Classifier Performance in Abusive Language Detection (Lopez Long et al., RANLP 2021)

ACL

• Holly Lopez Long, Alexandra O’Neil, and Sandra Kübler. 2021. On the Interaction between Annotation Quality and Classifier Performance in Abusive Language Detection. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 868–875, Held Online. INCOMA Ltd..