<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stoop-etal-2019-detecting">
    <titleInfo>
        <title>Detecting harassment in real-time as conversations develop</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wessel</namePart>
        <namePart type="family">Stoop</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Florian</namePart>
        <namePart type="family">Kunneman</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Antal</namePart>
        <namePart type="family">van den Bosch</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ben</namePart>
        <namePart type="family">Miller</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Third Workshop on Abusive Language Online</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sarah</namePart>
            <namePart type="given">T</namePart>
            <namePart type="family">Roberts</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joel</namePart>
            <namePart type="family">Tetreault</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vinodkumar</namePart>
            <namePart type="family">Prabhakaran</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Zeerak</namePart>
            <namePart type="family">Waseem</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We developed a machine-learning-based method to detect video game players that harass teammates or opponents in chat earlier in the conversation. This real-time technology would allow gaming companies to intervene during games, such as issue warnings or muting or banning a player. In a proof-of-concept experiment on League of Legends data we compute and visualize evaluation metrics for a machine learning classifier as conversations unfold, and observe that the optimal precision and recall of detecting toxic players at each moment in the conversation depends on the confidence threshold of the classifier: the threshold should start low, and increase as the conversation unfolds. How fast this sliding threshold should increase depends on the training set size.</abstract>
    <identifier type="citekey">stoop-etal-2019-detecting</identifier>
    <identifier type="doi">10.18653/v1/W19-3503</identifier>
    <location>
        <url>https://aclanthology.org/W19-3503</url>
    </location>
    <part>
        <date>2019-08</date>
        <extent unit="page">
            <start>19</start>
            <end>24</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Detecting harassment in real-time as conversations develop
%A Stoop, Wessel
%A Kunneman, Florian
%A van den Bosch, Antal
%A Miller, Ben
%Y Roberts, Sarah T.
%Y Tetreault, Joel
%Y Prabhakaran, Vinodkumar
%Y Waseem, Zeerak
%S Proceedings of the Third Workshop on Abusive Language Online
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F stoop-etal-2019-detecting
%X We developed a machine-learning-based method to detect video game players that harass teammates or opponents in chat earlier in the conversation. This real-time technology would allow gaming companies to intervene during games, such as issue warnings or muting or banning a player. In a proof-of-concept experiment on League of Legends data we compute and visualize evaluation metrics for a machine learning classifier as conversations unfold, and observe that the optimal precision and recall of detecting toxic players at each moment in the conversation depends on the confidence threshold of the classifier: the threshold should start low, and increase as the conversation unfolds. How fast this sliding threshold should increase depends on the training set size.
%R 10.18653/v1/W19-3503
%U https://aclanthology.org/W19-3503
%U https://doi.org/10.18653/v1/W19-3503
%P 19-24

Markdown (Informal)

[Detecting harassment in real-time as conversations develop](https://aclanthology.org/W19-3503) (Stoop et al., ALW 2019)

• Detecting harassment in real-time as conversations develop (Stoop et al., ALW 2019)

ACL

• Wessel Stoop, Florian Kunneman, Antal van den Bosch, and Ben Miller. 2019. Detecting harassment in real-time as conversations develop. In Proceedings of the Third Workshop on Abusive Language Online, pages 19–24, Florence, Italy. Association for Computational Linguistics.