Beyond hostile linguistic cues: The gravity of online milieu for hate speech detection in Arabic

Arijit Ghosh Chowdhury; Aniket Didolkar; Ramit Sawhney; Rajiv Ratn Shah

doi:10.1145/3342220.3344930

Beyond hostile linguistic cues: The gravity of online milieu for hate speech detection in Arabic

Arijit Ghosh Chowdhury, Aniket Didolkar, Ramit Sawhney, Rajiv Ratn Shah

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

Abstract

Religious Hate speech poses grave dangers for the cohesion of a democratic society, the protection of human rights and the rule of law. While previous work has shown that linguistic features can be effectively used for text categorization in Arabic, employing information coming from users'social networks has not yet been explored for such complex user characteristics. Systems relying on language information tend to have low precision because they tend to rely on messages containing particular terms indicating hate speech. In this paper, we study the novel problem of exploiting social context for detection of religious hate speech in Arabic tweets, given information extracted from their online milieu by learning a low-dimensional vector representation of users.

Original language	English
Title of host publication	HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media
Publisher	Association for Computing Machinery, Inc
Pages	285-286
Number of pages	2
ISBN (Electronic)	9781450368858
DOIs	https://doi.org/10.1145/3342220.3344930
Publication status	Published - 12-09-2019
Externally published	Yes
Event	30th ACM Conference on Hypertext and Social Media, HT 2019 - Hof, Germany Duration: 17-09-2019 → 20-09-2019

Publication series

Name	HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media

Conference

Conference	30th ACM Conference on Hypertext and Social Media, HT 2019
Country	Germany
City	Hof
Period	17-09-19 → 20-09-19

Fingerprint

All Science Journal Classification (ASJC) codes

Software
Artificial Intelligence
Human-Computer Interaction
Computer Graphics and Computer-Aided Design

Cite this

Chowdhury, A. G., Didolkar, A., Sawhney, R., & Shah, R. R. (2019). Beyond hostile linguistic cues: The gravity of online milieu for hate speech detection in Arabic. In HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media (pp. 285-286). (HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media). Association for Computing Machinery, Inc. https://doi.org/10.1145/3342220.3344930

Chowdhury, Arijit Ghosh ; Didolkar, Aniket ; Sawhney, Ramit ; Shah, Rajiv Ratn. / Beyond hostile linguistic cues : The gravity of online milieu for hate speech detection in Arabic. HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc, 2019. pp. 285-286 (HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media).

@inproceedings{f2d345cdd304422caa00a12648e4e395,

title = "Beyond hostile linguistic cues: The gravity of online milieu for hate speech detection in Arabic",

abstract = "Religious Hate speech poses grave dangers for the cohesion of a democratic society, the protection of human rights and the rule of law. While previous work has shown that linguistic features can be effectively used for text categorization in Arabic, employing information coming from users'social networks has not yet been explored for such complex user characteristics. Systems relying on language information tend to have low precision because they tend to rely on messages containing particular terms indicating hate speech. In this paper, we study the novel problem of exploiting social context for detection of religious hate speech in Arabic tweets, given information extracted from their online milieu by learning a low-dimensional vector representation of users.",

author = "Chowdhury, {Arijit Ghosh} and Aniket Didolkar and Ramit Sawhney and Shah, {Rajiv Ratn}",

year = "2019",

month = "9",

day = "12",

doi = "10.1145/3342220.3344930",

language = "English",

series = "HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media",

publisher = "Association for Computing Machinery, Inc",

pages = "285--286",

booktitle = "HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media",

note = "30th ACM Conference on Hypertext and Social Media, HT 2019 ; Conference date: 17-09-2019 Through 20-09-2019",

}

Chowdhury, AG, Didolkar, A, Sawhney, R & Shah, RR 2019, Beyond hostile linguistic cues: The gravity of online milieu for hate speech detection in Arabic. in HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media. HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media, Association for Computing Machinery, Inc, pp. 285-286, 30th ACM Conference on Hypertext and Social Media, HT 2019, Hof, Germany, 17-09-19. https://doi.org/10.1145/3342220.3344930

Beyond hostile linguistic cues : The gravity of online milieu for hate speech detection in Arabic. / Chowdhury, Arijit Ghosh; Didolkar, Aniket; Sawhney, Ramit; Shah, Rajiv Ratn.

HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc, 2019. p. 285-286 (HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media).

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

TY - GEN

T1 - Beyond hostile linguistic cues

T2 - 30th ACM Conference on Hypertext and Social Media, HT 2019

AU - Chowdhury, Arijit Ghosh

AU - Didolkar, Aniket

AU - Sawhney, Ramit

AU - Shah, Rajiv Ratn

PY - 2019/9/12

Y1 - 2019/9/12

N2 - Religious Hate speech poses grave dangers for the cohesion of a democratic society, the protection of human rights and the rule of law. While previous work has shown that linguistic features can be effectively used for text categorization in Arabic, employing information coming from users'social networks has not yet been explored for such complex user characteristics. Systems relying on language information tend to have low precision because they tend to rely on messages containing particular terms indicating hate speech. In this paper, we study the novel problem of exploiting social context for detection of religious hate speech in Arabic tweets, given information extracted from their online milieu by learning a low-dimensional vector representation of users.

AB - Religious Hate speech poses grave dangers for the cohesion of a democratic society, the protection of human rights and the rule of law. While previous work has shown that linguistic features can be effectively used for text categorization in Arabic, employing information coming from users'social networks has not yet been explored for such complex user characteristics. Systems relying on language information tend to have low precision because they tend to rely on messages containing particular terms indicating hate speech. In this paper, we study the novel problem of exploiting social context for detection of religious hate speech in Arabic tweets, given information extracted from their online milieu by learning a low-dimensional vector representation of users.

UR - http://www.scopus.com/inward/record.url?scp=85073359488&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073359488&partnerID=8YFLogxK

U2 - 10.1145/3342220.3344930

DO - 10.1145/3342220.3344930

M3 - Conference contribution

AN - SCOPUS:85073359488

T3 - HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media

SP - 285

EP - 286

BT - HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media

PB - Association for Computing Machinery, Inc

Y2 - 17 September 2019 through 20 September 2019

ER -

Chowdhury AG, Didolkar A, Sawhney R, Shah RR. Beyond hostile linguistic cues: The gravity of online milieu for hate speech detection in Arabic. In HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc. 2019. p. 285-286. (HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media). https://doi.org/10.1145/3342220.3344930

Access to Document

10.1145/3342220.3344930