@inproceedings{salawu-etal-2021-large,
title = "A Large-Scale {E}nglish Multi-Label {T}witter Dataset for Cyberbullying and Online Abuse Detection",
author = "Salawu, Semiu and
Lumsden, Jo and
He, Yulan",
editor = "Mostafazadeh Davani, Aida and
Kiela, Douwe and
Lambert, Mathias and
Vidgen, Bertie and
Prabhakaran, Vinodkumar and
Waseem, Zeerak",
booktitle = "Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.woah-1.16",
doi = "10.18653/v1/2021.woah-1.16",
pages = "146--156",
abstract = "In this paper, we introduce a new English Twitter-based dataset for cyberbullying detection and online abuse. Comprising 62,587 tweets, this dataset was sourced from Twitter using specific query terms designed to retrieve tweets with high probabilities of various forms of bullying and offensive content, including insult, trolling, profanity, sarcasm, threat, porn and exclusion. We recruited a pool of 17 annotators to perform fine-grained annotation on the dataset with each tweet annotated by three annotators. All our annotators are high school educated and frequent users of social media. Inter-rater agreement for the dataset as measured by Krippendorff{'}s Alpha is 0.67. Analysis performed on the dataset confirmed common cyberbullying themes reported by other studies and revealed interesting relationships between the classes. The dataset was used to train a number of transformer-based deep learning models returning impressive results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="salawu-etal-2021-large">
<titleInfo>
<title>A Large-Scale English Multi-Label Twitter Dataset for Cyberbullying and Online Abuse Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Semiu</namePart>
<namePart type="family">Salawu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jo</namePart>
<namePart type="family">Lumsden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)</title>
</titleInfo>
<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">Douwe</namePart>
<namePart type="family">Kiela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathias</namePart>
<namePart type="family">Lambert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bertie</namePart>
<namePart type="family">Vidgen</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">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we introduce a new English Twitter-based dataset for cyberbullying detection and online abuse. Comprising 62,587 tweets, this dataset was sourced from Twitter using specific query terms designed to retrieve tweets with high probabilities of various forms of bullying and offensive content, including insult, trolling, profanity, sarcasm, threat, porn and exclusion. We recruited a pool of 17 annotators to perform fine-grained annotation on the dataset with each tweet annotated by three annotators. All our annotators are high school educated and frequent users of social media. Inter-rater agreement for the dataset as measured by Krippendorff’s Alpha is 0.67. Analysis performed on the dataset confirmed common cyberbullying themes reported by other studies and revealed interesting relationships between the classes. The dataset was used to train a number of transformer-based deep learning models returning impressive results.</abstract>
<identifier type="citekey">salawu-etal-2021-large</identifier>
<identifier type="doi">10.18653/v1/2021.woah-1.16</identifier>
<location>
<url>https://aclanthology.org/2021.woah-1.16</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>146</start>
<end>156</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Large-Scale English Multi-Label Twitter Dataset for Cyberbullying and Online Abuse Detection
%A Salawu, Semiu
%A Lumsden, Jo
%A He, Yulan
%Y Mostafazadeh Davani, Aida
%Y Kiela, Douwe
%Y Lambert, Mathias
%Y Vidgen, Bertie
%Y Prabhakaran, Vinodkumar
%Y Waseem, Zeerak
%S Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F salawu-etal-2021-large
%X In this paper, we introduce a new English Twitter-based dataset for cyberbullying detection and online abuse. Comprising 62,587 tweets, this dataset was sourced from Twitter using specific query terms designed to retrieve tweets with high probabilities of various forms of bullying and offensive content, including insult, trolling, profanity, sarcasm, threat, porn and exclusion. We recruited a pool of 17 annotators to perform fine-grained annotation on the dataset with each tweet annotated by three annotators. All our annotators are high school educated and frequent users of social media. Inter-rater agreement for the dataset as measured by Krippendorff’s Alpha is 0.67. Analysis performed on the dataset confirmed common cyberbullying themes reported by other studies and revealed interesting relationships between the classes. The dataset was used to train a number of transformer-based deep learning models returning impressive results.
%R 10.18653/v1/2021.woah-1.16
%U https://aclanthology.org/2021.woah-1.16
%U https://doi.org/10.18653/v1/2021.woah-1.16
%P 146-156
Markdown (Informal)
[A Large-Scale English Multi-Label Twitter Dataset for Cyberbullying and Online Abuse Detection](https://aclanthology.org/2021.woah-1.16) (Salawu et al., WOAH 2021)
ACL