<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pavlopoulos-likas-2024-polarized">
    <titleInfo>
        <title>Polarized Opinion Detection Improves the Detection of Toxic Language</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">John</namePart>
        <namePart type="family">Pavlopoulos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aristidis</namePart>
        <namePart type="family">Likas</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yvette</namePart>
            <namePart type="family">Graham</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthew</namePart>
            <namePart type="family">Purver</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">St. Julian’s, Malta</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Distance from unimodality (DFU) has been found to correlate well with human judgment for the assessment of polarized opinions. However, its un-normalized nature makes it less intuitive and somewhat difficult to exploit in machine learning (e.g., as a supervised signal). In this work a normalized version of this measure, called nDFU, is proposed that leads to better assessment of the degree of polarization. Then, we propose a methodology for K-class text classification, based on nDFU, that exploits polarized texts in the dataset. Such polarized instances are assigned to a separate K+1 class, so that a K+1-class classifier is trained. An empirical analysis on three datasets for abusive language detection, shows that nDFU can be used to model polarized annotations and prevent them from harming the classification performance. Finally, we further exploit nDFU to specify conditions that could explain polarization given a dimension and present text examples that polarized the annotators when the dimension was gender and race. Our code is available at https://github.com/ipavlopoulos/ndfu.</abstract>
    <identifier type="citekey">pavlopoulos-likas-2024-polarized</identifier>
    <location>
        <url>https://aclanthology.org/2024.eacl-long.117</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>1946</start>
            <end>1958</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Polarized Opinion Detection Improves the Detection of Toxic Language
%A Pavlopoulos, John
%A Likas, Aristidis
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F pavlopoulos-likas-2024-polarized
%X Distance from unimodality (DFU) has been found to correlate well with human judgment for the assessment of polarized opinions. However, its un-normalized nature makes it less intuitive and somewhat difficult to exploit in machine learning (e.g., as a supervised signal). In this work a normalized version of this measure, called nDFU, is proposed that leads to better assessment of the degree of polarization. Then, we propose a methodology for K-class text classification, based on nDFU, that exploits polarized texts in the dataset. Such polarized instances are assigned to a separate K+1 class, so that a K+1-class classifier is trained. An empirical analysis on three datasets for abusive language detection, shows that nDFU can be used to model polarized annotations and prevent them from harming the classification performance. Finally, we further exploit nDFU to specify conditions that could explain polarization given a dimension and present text examples that polarized the annotators when the dimension was gender and race. Our code is available at https://github.com/ipavlopoulos/ndfu.
%U https://aclanthology.org/2024.eacl-long.117
%P 1946-1958

Markdown (Informal)

[Polarized Opinion Detection Improves the Detection of Toxic Language](https://aclanthology.org/2024.eacl-long.117) (Pavlopoulos & Likas, EACL 2024)

• Polarized Opinion Detection Improves the Detection of Toxic Language (Pavlopoulos & Likas, EACL 2024)

ACL

• John Pavlopoulos and Aristidis Likas. 2024. Polarized Opinion Detection Improves the Detection of Toxic Language. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1946–1958, St. Julian’s, Malta. Association for Computational Linguistics.