@inproceedings{pamungkas-etal-2020-really,
title = "Do You Really Want to Hurt Me? Predicting Abusive Swearing in Social Media",
author = "Pamungkas, Endang Wahyu and
Basile, Valerio and
Patti, Viviana",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.765",
pages = "6237--6246",
abstract = "Swearing plays an ubiquitous role in everyday conversations among humans, both in oral and textual communication, and occurs frequently in social media texts, typically featured by informal language and spontaneous writing. Such occurrences can be linked to an abusive context, when they contribute to the expression of hatred and to the abusive effect, causing harm and offense. However, swearing is multifaceted and is often used in casual contexts, also with positive social functions. In this study, we explore the phenomenon of swearing in Twitter conversations, taking the possibility of predicting the abusiveness of a swear word in a tweet context as the main investigation perspective. We developed the Twitter English corpus SWAD (Swear Words Abusiveness Dataset), where abusive swearing is manually annotated at the word level. Our collection consists of 1,511 unique swear words from 1,320 tweets. We developed models to automatically predict abusive swearing, to provide an intrinsic evaluation of SWAD and confirm the robustness of the resource. We also present the results of a glass box ablation study in order to investigate which lexical, syntactic, and affective features are more informative towards the automatic prediction of the function of swearing.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pamungkas-etal-2020-really">
<titleInfo>
<title>Do You Really Want to Hurt Me? Predicting Abusive Swearing in Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Endang</namePart>
<namePart type="given">Wahyu</namePart>
<namePart type="family">Pamungkas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviana</namePart>
<namePart type="family">Patti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Swearing plays an ubiquitous role in everyday conversations among humans, both in oral and textual communication, and occurs frequently in social media texts, typically featured by informal language and spontaneous writing. Such occurrences can be linked to an abusive context, when they contribute to the expression of hatred and to the abusive effect, causing harm and offense. However, swearing is multifaceted and is often used in casual contexts, also with positive social functions. In this study, we explore the phenomenon of swearing in Twitter conversations, taking the possibility of predicting the abusiveness of a swear word in a tweet context as the main investigation perspective. We developed the Twitter English corpus SWAD (Swear Words Abusiveness Dataset), where abusive swearing is manually annotated at the word level. Our collection consists of 1,511 unique swear words from 1,320 tweets. We developed models to automatically predict abusive swearing, to provide an intrinsic evaluation of SWAD and confirm the robustness of the resource. We also present the results of a glass box ablation study in order to investigate which lexical, syntactic, and affective features are more informative towards the automatic prediction of the function of swearing.</abstract>
<identifier type="citekey">pamungkas-etal-2020-really</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.765</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6237</start>
<end>6246</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do You Really Want to Hurt Me? Predicting Abusive Swearing in Social Media
%A Pamungkas, Endang Wahyu
%A Basile, Valerio
%A Patti, Viviana
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F pamungkas-etal-2020-really
%X Swearing plays an ubiquitous role in everyday conversations among humans, both in oral and textual communication, and occurs frequently in social media texts, typically featured by informal language and spontaneous writing. Such occurrences can be linked to an abusive context, when they contribute to the expression of hatred and to the abusive effect, causing harm and offense. However, swearing is multifaceted and is often used in casual contexts, also with positive social functions. In this study, we explore the phenomenon of swearing in Twitter conversations, taking the possibility of predicting the abusiveness of a swear word in a tweet context as the main investigation perspective. We developed the Twitter English corpus SWAD (Swear Words Abusiveness Dataset), where abusive swearing is manually annotated at the word level. Our collection consists of 1,511 unique swear words from 1,320 tweets. We developed models to automatically predict abusive swearing, to provide an intrinsic evaluation of SWAD and confirm the robustness of the resource. We also present the results of a glass box ablation study in order to investigate which lexical, syntactic, and affective features are more informative towards the automatic prediction of the function of swearing.
%U https://aclanthology.org/2020.lrec-1.765
%P 6237-6246
Markdown (Informal)
[Do You Really Want to Hurt Me? Predicting Abusive Swearing in Social Media](https://aclanthology.org/2020.lrec-1.765) (Pamungkas et al., LREC 2020)
ACL