One-step and two-step classification for abusive language detection on twitter

Ji Ho Park; Pascale Fung

One-step and two-step classification for abusive language detection on twitter

Ji Ho Park, Pascale Fung

Department of Electronic and Computer Engineering

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

165 Citations (Scopus)

Abstract

Automatic abusive language detection is a difficult but important task for online social media. Our research explores a two-step approach of performing classification on abusive language and then classifying into specific types and compares it with one-step approach of doing one multi-class classification for detecting sexist and racist languages. With a public English Twitter corpus of 20 thousand tweets in the type of sexism and racism, our approach shows a promising performance of 0.827 F-measure by using HybridCNN in one-step and 0.824 F-measure by using logistic regression in two-steps.

Original language	English
Title of host publication	1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop
Editors	Zeerak Waseem, Wendy Hui Kyong Chung, Dirk Hovy, Joel Tetreault
Publisher	Association for Computational Linguistics (ACL)
Pages	41-45
Number of pages	5
ISBN (Electronic)	9781945626661
Publication status	Published - 2017
Event	1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop - Vancouver, Canada Duration: 4 Aug 2017 → …

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)	0736-587X

Conference

Conference	1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop
Country/Territory	Canada
City	Vancouver
Period	4/08/17 → …

Bibliographical note

Publisher Copyright:
© 2017 Association for Computational Linguistics

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 5 Gender Equality

Cite this

Park, J. H., & Fung, P. (2017). One-step and two-step classification for abusive language detection on twitter. In Z. Waseem, W. H. K. Chung, D. Hovy, & J. Tetreault (Eds.), 1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop (pp. 41-45). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics (ACL).

Park, Ji Ho ; Fung, Pascale. / One-step and two-step classification for abusive language detection on twitter. 1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop. editor / Zeerak Waseem ; Wendy Hui Kyong Chung ; Dirk Hovy ; Joel Tetreault. Association for Computational Linguistics (ACL), 2017. pp. 41-45 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{2d936b5a64b24454bc4f07f6702ef4ad,

title = "One-step and two-step classification for abusive language detection on twitter",

abstract = "Automatic abusive language detection is a difficult but important task for online social media. Our research explores a two-step approach of performing classification on abusive language and then classifying into specific types and compares it with one-step approach of doing one multi-class classification for detecting sexist and racist languages. With a public English Twitter corpus of 20 thousand tweets in the type of sexism and racism, our approach shows a promising performance of 0.827 F-measure by using HybridCNN in one-step and 0.824 F-measure by using logistic regression in two-steps.",

author = "Park, \{Ji Ho\} and Pascale Fung",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics; 1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop ; Conference date: 04-08-2017",

year = "2017",

language = "English",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

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

pages = "41--45",

editor = "Zeerak Waseem and Chung, \{Wendy Hui Kyong\} and Dirk Hovy and Joel Tetreault",

booktitle = "1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop",

}

Park, JH & Fung, P 2017, One-step and two-step classification for abusive language detection on twitter. in Z Waseem, WHK Chung, D Hovy & J Tetreault (eds), 1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL), pp. 41-45, 1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop, Vancouver, Canada, 4/08/17.

One-step and two-step classification for abusive language detection on twitter. / Park, Ji Ho; Fung, Pascale.
1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop. ed. / Zeerak Waseem; Wendy Hui Kyong Chung; Dirk Hovy; Joel Tetreault. Association for Computational Linguistics (ACL), 2017. p. 41-45 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - One-step and two-step classification for abusive language detection on twitter

AU - Park, Ji Ho

AU - Fung, Pascale

PY - 2017

Y1 - 2017

N2 - Automatic abusive language detection is a difficult but important task for online social media. Our research explores a two-step approach of performing classification on abusive language and then classifying into specific types and compares it with one-step approach of doing one multi-class classification for detecting sexist and racist languages. With a public English Twitter corpus of 20 thousand tweets in the type of sexism and racism, our approach shows a promising performance of 0.827 F-measure by using HybridCNN in one-step and 0.824 F-measure by using logistic regression in two-steps.

AB - Automatic abusive language detection is a difficult but important task for online social media. Our research explores a two-step approach of performing classification on abusive language and then classifying into specific types and compares it with one-step approach of doing one multi-class classification for detecting sexist and racist languages. With a public English Twitter corpus of 20 thousand tweets in the type of sexism and racism, our approach shows a promising performance of 0.827 F-measure by using HybridCNN in one-step and 0.824 F-measure by using logistic regression in two-steps.

UR - https://www.scopus.com/pages/publications/85104639200

M3 - Conference Paper published in a book

AN - SCOPUS:85104639200

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 41

EP - 45

BT - 1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop

A2 - Waseem, Zeerak

A2 - Chung, Wendy Hui Kyong

A2 - Hovy, Dirk

A2 - Tetreault, Joel

PB - Association for Computational Linguistics (ACL)

T2 - 1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop

Y2 - 4 August 2017

ER -

Park JH, Fung P. One-step and two-step classification for abusive language detection on twitter. In Waseem Z, Chung WHK, Hovy D, Tetreault J, editors, 1st Workshop on Abusive Language Online, ALW 2017 at the 55th Annual Meeting of the Association for Computational Linguistic, ACL 2017 - Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2017. p. 41-45. (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

One-step and two-step classification for abusive language detection on twitter

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Other files and links

Fingerprint

Cite this