Abusive Language Detection on Arabic Social Media

Hamdy  Mubarak; Kareem Darwish; Walid Magdy

doi:10.18653/v1/W17-3008

Abusive Language Detection on Arabic Social Media

Hamdy Mubarak, Kareem Darwish, Walid Magdy

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

In this paper, we present our work on detecting abusive language on Arabic social media. We extract a list of obscene words and hashtags using common patterns used in offensive and rude communications. We also classify Twitter users according to whether they use any of these words or not in their tweets. We expand the list of obscene words using this classification, and we report results on a newly created dataset of classified Arabic tweets (obscene, offensive, and clean). We make this dataset freely available for research, in addition to the list of obscene words and hashtags. We are also publicly releasing a large corpus of classified user comments that were deleted from a popular Arabic news site due to violations the site’s rules and guidelines.

Original language	English
Title of host publication	Proceedings of the First Workshop on Abusive Language Online
Publisher	Association for Computational Linguistics (ACL)
Pages	52–56
Number of pages	5
ISBN (Print)	978-1-945626-66-1
DOIs	https://doi.org/10.18653/v1/W17-3008
Publication status	Published - 4 Aug 2017
Event	First Workshop on Abusive Language Online 2017 - Vancouver, Canada Duration: 4 Aug 2017 → 4 Aug 2017 https://sites.google.com/site/abusivelanguageworkshop2017/

Conference

Conference	First Workshop on Abusive Language Online 2017
Abbreviated title	ALW1 2017
Country/Territory	Canada
City	Vancouver
Period	4/08/17 → 4/08/17
Internet address	https://sites.google.com/site/abusivelanguageworkshop2017/

Access to Document

10.18653/v1/W17-3008Licence: Creative Commons: Attribution (CC-BY)

W17-3008Final published version, 370 KBLicence: Creative Commons: Attribution (CC-BY)

http://aclweb.org/anthology/W17-3008Licence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{0b50618e87e449f88b1c9bfe2c515aa3,

title = "Abusive Language Detection on Arabic Social Media",

abstract = "In this paper, we present our work on detecting abusive language on Arabic social media. We extract a list of obscene words and hashtags using common patterns used in offensive and rude communications. We also classify Twitter users according to whether they use any of these words or not in their tweets. We expand the list of obscene words using this classification, and we report results on a newly created dataset of classified Arabic tweets (obscene, offensive, and clean). We make this dataset freely available for research, in addition to the list of obscene words and hashtags. We are also publicly releasing a large corpus of classified user comments that were deleted from a popular Arabic news site due to violations the site{\textquoteright}s rules and guidelines.",

author = "Hamdy Mubarak and Kareem Darwish and Walid Magdy",

year = "2017",

month = aug,

day = "4",

doi = "10.18653/v1/W17-3008",

language = "English",

isbn = "978-1-945626-66-1",

pages = "52–56",

booktitle = "Proceedings of the First Workshop on Abusive Language Online",

publisher = "Association for Computational Linguistics (ACL)",

note = "First Workshop on Abusive Language Online 2017, ALW1 2017 ; Conference date: 04-08-2017 Through 04-08-2017",

url = "https://sites.google.com/site/abusivelanguageworkshop2017/",

}

TY - GEN

T1 - Abusive Language Detection on Arabic Social Media

AU - Mubarak, Hamdy

AU - Darwish, Kareem

AU - Magdy, Walid

PY - 2017/8/4

Y1 - 2017/8/4

N2 - In this paper, we present our work on detecting abusive language on Arabic social media. We extract a list of obscene words and hashtags using common patterns used in offensive and rude communications. We also classify Twitter users according to whether they use any of these words or not in their tweets. We expand the list of obscene words using this classification, and we report results on a newly created dataset of classified Arabic tweets (obscene, offensive, and clean). We make this dataset freely available for research, in addition to the list of obscene words and hashtags. We are also publicly releasing a large corpus of classified user comments that were deleted from a popular Arabic news site due to violations the site’s rules and guidelines.

AB - In this paper, we present our work on detecting abusive language on Arabic social media. We extract a list of obscene words and hashtags using common patterns used in offensive and rude communications. We also classify Twitter users according to whether they use any of these words or not in their tweets. We expand the list of obscene words using this classification, and we report results on a newly created dataset of classified Arabic tweets (obscene, offensive, and clean). We make this dataset freely available for research, in addition to the list of obscene words and hashtags. We are also publicly releasing a large corpus of classified user comments that were deleted from a popular Arabic news site due to violations the site’s rules and guidelines.

U2 - 10.18653/v1/W17-3008

DO - 10.18653/v1/W17-3008

M3 - Conference contribution

SN - 978-1-945626-66-1

SP - 52

EP - 56

BT - Proceedings of the First Workshop on Abusive Language Online

PB - Association for Computational Linguistics (ACL)

T2 - First Workshop on Abusive Language Online 2017

Y2 - 4 August 2017 through 4 August 2017

ER -

Abusive Language Detection on Arabic Social Media

Abstract / Description of output

Conference

Access to Document

Fingerprint

Cite this