@inproceedings{caines-etal-2018-aggressive,
title = "Aggressive language in an online hacking forum",
author = "Caines, Andrew and
Pastrana, Sergio and
Hutchings, Alice and
Buttery, Paula",
editor = "Fi{\v{s}}er, Darja and
Huang, Ruihong and
Prabhakaran, Vinodkumar and
Voigt, Rob and
Waseem, Zeerak and
Wernimont, Jacqueline",
booktitle = "Proceedings of the 2nd Workshop on Abusive Language Online ({ALW}2)",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5109",
doi = "10.18653/v1/W18-5109",
pages = "66--74",
abstract = "We probe the heterogeneity in levels of abusive language in different sections of the Internet, using an annotated corpus of Wikipedia page edit comments to train a binary classifier for abuse detection. Our test data come from the CrimeBB Corpus of hacking-related forum posts and we find that (a) forum interactions are rarely abusive, (b) the abusive language which does exist tends to be relatively mild compared to that found in the Wikipedia comments domain, and tends to involve aggressive posturing rather than hate speech or threats of violence. We observe that the purpose of conversations in online forums tend to be more constructive and informative than those in Wikipedia page edit comments which are geared more towards adversarial interactions, and that this may explain the lower levels of abuse found in our forum data than in Wikipedia comments. Further work remains to be done to compare these results with other inter-domain classification experiments, and to understand the impact of aggressive language in forum conversations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="caines-etal-2018-aggressive">
<titleInfo>
<title>Aggressive language in an online hacking forum</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Caines</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sergio</namePart>
<namePart type="family">Pastrana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alice</namePart>
<namePart type="family">Hutchings</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Buttery</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</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">Rob</namePart>
<namePart type="family">Voigt</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>
<name type="personal">
<namePart type="given">Jacqueline</namePart>
<namePart type="family">Wernimont</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We probe the heterogeneity in levels of abusive language in different sections of the Internet, using an annotated corpus of Wikipedia page edit comments to train a binary classifier for abuse detection. Our test data come from the CrimeBB Corpus of hacking-related forum posts and we find that (a) forum interactions are rarely abusive, (b) the abusive language which does exist tends to be relatively mild compared to that found in the Wikipedia comments domain, and tends to involve aggressive posturing rather than hate speech or threats of violence. We observe that the purpose of conversations in online forums tend to be more constructive and informative than those in Wikipedia page edit comments which are geared more towards adversarial interactions, and that this may explain the lower levels of abuse found in our forum data than in Wikipedia comments. Further work remains to be done to compare these results with other inter-domain classification experiments, and to understand the impact of aggressive language in forum conversations.</abstract>
<identifier type="citekey">caines-etal-2018-aggressive</identifier>
<identifier type="doi">10.18653/v1/W18-5109</identifier>
<location>
<url>https://aclanthology.org/W18-5109</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>66</start>
<end>74</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aggressive language in an online hacking forum
%A Caines, Andrew
%A Pastrana, Sergio
%A Hutchings, Alice
%A Buttery, Paula
%Y Fišer, Darja
%Y Huang, Ruihong
%Y Prabhakaran, Vinodkumar
%Y Voigt, Rob
%Y Waseem, Zeerak
%Y Wernimont, Jacqueline
%S Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F caines-etal-2018-aggressive
%X We probe the heterogeneity in levels of abusive language in different sections of the Internet, using an annotated corpus of Wikipedia page edit comments to train a binary classifier for abuse detection. Our test data come from the CrimeBB Corpus of hacking-related forum posts and we find that (a) forum interactions are rarely abusive, (b) the abusive language which does exist tends to be relatively mild compared to that found in the Wikipedia comments domain, and tends to involve aggressive posturing rather than hate speech or threats of violence. We observe that the purpose of conversations in online forums tend to be more constructive and informative than those in Wikipedia page edit comments which are geared more towards adversarial interactions, and that this may explain the lower levels of abuse found in our forum data than in Wikipedia comments. Further work remains to be done to compare these results with other inter-domain classification experiments, and to understand the impact of aggressive language in forum conversations.
%R 10.18653/v1/W18-5109
%U https://aclanthology.org/W18-5109
%U https://doi.org/10.18653/v1/W18-5109
%P 66-74
Markdown (Informal)
[Aggressive language in an online hacking forum](https://aclanthology.org/W18-5109) (Caines et al., ALW 2018)
ACL
- Andrew Caines, Sergio Pastrana, Alice Hutchings, and Paula Buttery. 2018. Aggressive language in an online hacking forum. In Proceedings of the 2nd Workshop on Abusive Language Online (ALW2), pages 66–74, Brussels, Belgium. Association for Computational Linguistics.