@inproceedings{zhang-etal-2024-study-class,
title = "A Study of the Class Imbalance Problem in Abusive Language Detection",
author = "Zhang, Yaqi and
Hangya, Viktor and
Fraser, Alexander",
editor = {Chung, Yi-Ling and
Talat, Zeerak and
Nozza, Debora and
Plaza-del-Arco, Flor Miriam and
R{\"o}ttger, Paul and
Mostafazadeh Davani, Aida and
Calabrese, Agostina},
booktitle = "Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.woah-1.4/",
doi = "10.18653/v1/2024.woah-1.4",
pages = "38--51",
abstract = "Abusive language detection has drawn increasing interest in recent years. However, a less systematically explored obstacle is label imbalance, i.e., the amount of abusive data is much lower than non-abusive data, leading to performance issues. The aim of this work is to conduct a comprehensive comparative study of popular methods for addressing the class imbalance issue. We explore 10 well-known approaches on 8 datasets with distinct characteristics: binary or multi-class, moderately or largely imbalanced, focusing on various types of abuse, etc. Additionally, we pro-pose two novel methods specialized for abuse detection: AbusiveLexiconAug and ExternalDataAug, which enrich the training data using abusive lexicons and external abusive datasets, respectively. We conclude that: 1) our AbusiveLexiconAug approach, random oversampling, and focal loss are the most versatile methods on various datasets; 2) focal loss tends to yield peak model performance; 3) oversampling and focal loss provide promising results for binary datasets and small multi-class sets, while undersampling and weighted cross-entropy are more suitable for large multi-class sets; 4) most methods are sensitive to hyperparameters, yet our suggested choice of hyperparameters provides a good starting point."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-study-class">
<titleInfo>
<title>A Study of the Class Imbalance Problem in Abusive Language Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaqi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viktor</namePart>
<namePart type="family">Hangya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Fraser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yi-Ling</namePart>
<namePart type="family">Chung</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>
<name type="personal">
<namePart type="given">Debora</namePart>
<namePart type="family">Nozza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flor</namePart>
<namePart type="given">Miriam</namePart>
<namePart type="family">Plaza-del-Arco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Röttger</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">Agostina</namePart>
<namePart type="family">Calabrese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Abusive language detection has drawn increasing interest in recent years. However, a less systematically explored obstacle is label imbalance, i.e., the amount of abusive data is much lower than non-abusive data, leading to performance issues. The aim of this work is to conduct a comprehensive comparative study of popular methods for addressing the class imbalance issue. We explore 10 well-known approaches on 8 datasets with distinct characteristics: binary or multi-class, moderately or largely imbalanced, focusing on various types of abuse, etc. Additionally, we pro-pose two novel methods specialized for abuse detection: AbusiveLexiconAug and ExternalDataAug, which enrich the training data using abusive lexicons and external abusive datasets, respectively. We conclude that: 1) our AbusiveLexiconAug approach, random oversampling, and focal loss are the most versatile methods on various datasets; 2) focal loss tends to yield peak model performance; 3) oversampling and focal loss provide promising results for binary datasets and small multi-class sets, while undersampling and weighted cross-entropy are more suitable for large multi-class sets; 4) most methods are sensitive to hyperparameters, yet our suggested choice of hyperparameters provides a good starting point.</abstract>
<identifier type="citekey">zhang-etal-2024-study-class</identifier>
<identifier type="doi">10.18653/v1/2024.woah-1.4</identifier>
<location>
<url>https://aclanthology.org/2024.woah-1.4/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>38</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Study of the Class Imbalance Problem in Abusive Language Detection
%A Zhang, Yaqi
%A Hangya, Viktor
%A Fraser, Alexander
%Y Chung, Yi-Ling
%Y Talat, Zeerak
%Y Nozza, Debora
%Y Plaza-del-Arco, Flor Miriam
%Y Röttger, Paul
%Y Mostafazadeh Davani, Aida
%Y Calabrese, Agostina
%S Proceedings of the 8th Workshop on Online Abuse and Harms (WOAH 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zhang-etal-2024-study-class
%X Abusive language detection has drawn increasing interest in recent years. However, a less systematically explored obstacle is label imbalance, i.e., the amount of abusive data is much lower than non-abusive data, leading to performance issues. The aim of this work is to conduct a comprehensive comparative study of popular methods for addressing the class imbalance issue. We explore 10 well-known approaches on 8 datasets with distinct characteristics: binary or multi-class, moderately or largely imbalanced, focusing on various types of abuse, etc. Additionally, we pro-pose two novel methods specialized for abuse detection: AbusiveLexiconAug and ExternalDataAug, which enrich the training data using abusive lexicons and external abusive datasets, respectively. We conclude that: 1) our AbusiveLexiconAug approach, random oversampling, and focal loss are the most versatile methods on various datasets; 2) focal loss tends to yield peak model performance; 3) oversampling and focal loss provide promising results for binary datasets and small multi-class sets, while undersampling and weighted cross-entropy are more suitable for large multi-class sets; 4) most methods are sensitive to hyperparameters, yet our suggested choice of hyperparameters provides a good starting point.
%R 10.18653/v1/2024.woah-1.4
%U https://aclanthology.org/2024.woah-1.4/
%U https://doi.org/10.18653/v1/2024.woah-1.4
%P 38-51
Markdown (Informal)
[A Study of the Class Imbalance Problem in Abusive Language Detection](https://aclanthology.org/2024.woah-1.4/) (Zhang et al., WOAH 2024)
ACL