JCTDHS at SemEval-2019 task 5: Detection of hate speech in tweets using deep learning methods, character N-gram features, and preprocessing methods

Yaakov HaCohen-Kerner; Elyashiv Shayovitz; Shalom Rochman; Eli Cahn; Gal Didi; Ziv Ben-David

JCTDHS at SemEval-2019 task 5: Detection of hate speech in tweets using deep learning methods, character N-gram features, and preprocessing methods

Yaakov HaCohen-Kerner, Elyashiv Shayovitz, Shalom Rochman, Eli Cahn, Gal Didi, Ziv Ben-David

Jerusalem College of Technology

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

3 Scopus citations

Abstract

In this paper, we describe our submissions to SemEval-2019 contest. We tackled subtask A - “a binary classification where systems have to predict whether a tweet with a given target (women or immigrants) is hateful or not hateful”, a part of task 5 “Multilingual detection of hate speech against immigrants and women in Twitter (HatEval)”. Our system JCTDHS (Jerusalem College of Technology Detects Hate Speech) was developed for tweets written in English. We applied various supervised ML methods, various combinations of n-gram features using the TF-IDF scheme. In addition, we applied various combinations of eight basic preprocessing methods. Our best submission was a special bidirectional RNN, which was ranked at the 11^th position out of 68 submissions.

Original language	English
Title of host publication	NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop
Publisher	Association for Computational Linguistics (ACL)
Pages	426-430
Number of pages	5
ISBN (Electronic)	9781950737062
State	Published - 2019
Externally published	Yes
Event	13th International Workshop on Semantic Evaluation, SemEval 2019, co-located with the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019 - Minneapolis, United States Duration: 6 Jun 2019 → 7 Jun 2019

Publication series

Name	NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop

Conference

Conference	13th International Workshop on Semantic Evaluation, SemEval 2019, co-located with the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019
Country/Territory	United States
City	Minneapolis
Period	6/06/19 → 7/06/19

Bibliographical note

Publisher Copyright:
© 2019 Association for Computational Linguistics

Cite this

HaCohen-Kerner, Y., Shayovitz, E., Rochman, S., Cahn, E., Didi, G., & Ben-David, Z. (2019). JCTDHS at SemEval-2019 task 5: Detection of hate speech in tweets using deep learning methods, character N-gram features, and preprocessing methods. In NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop (pp. 426-430). (NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop). Association for Computational Linguistics (ACL).

HaCohen-Kerner, Yaakov ; Shayovitz, Elyashiv ; Rochman, Shalom et al. / JCTDHS at SemEval-2019 task 5 : Detection of hate speech in tweets using deep learning methods, character N-gram features, and preprocessing methods. NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop. Association for Computational Linguistics (ACL), 2019. pp. 426-430 (NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop).

@inproceedings{c05a394fc91d41a3ad3d9542b7780380,

title = "JCTDHS at SemEval-2019 task 5: Detection of hate speech in tweets using deep learning methods, character N-gram features, and preprocessing methods",

abstract = "In this paper, we describe our submissions to SemEval-2019 contest. We tackled subtask A - “a binary classification where systems have to predict whether a tweet with a given target (women or immigrants) is hateful or not hateful”, a part of task 5 “Multilingual detection of hate speech against immigrants and women in Twitter (HatEval)”. Our system JCTDHS (Jerusalem College of Technology Detects Hate Speech) was developed for tweets written in English. We applied various supervised ML methods, various combinations of n-gram features using the TF-IDF scheme. In addition, we applied various combinations of eight basic preprocessing methods. Our best submission was a special bidirectional RNN, which was ranked at the 11th position out of 68 submissions.",

author = "Yaakov HaCohen-Kerner and Elyashiv Shayovitz and Shalom Rochman and Eli Cahn and Gal Didi and Ziv Ben-David",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computational Linguistics; 13th International Workshop on Semantic Evaluation, SemEval 2019, co-located with the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019 ; Conference date: 06-06-2019 Through 07-06-2019",

year = "2019",

language = "אנגלית",

series = "NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop",

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

pages = "426--430",

booktitle = "NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop",

address = "ארצות הברית",

}

HaCohen-Kerner, Y, Shayovitz, E, Rochman, S, Cahn, E, Didi, G & Ben-David, Z 2019, JCTDHS at SemEval-2019 task 5: Detection of hate speech in tweets using deep learning methods, character N-gram features, and preprocessing methods. in NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop. NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop, Association for Computational Linguistics (ACL), pp. 426-430, 13th International Workshop on Semantic Evaluation, SemEval 2019, co-located with the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019, Minneapolis, United States, 6/06/19.

JCTDHS at SemEval-2019 task 5: Detection of hate speech in tweets using deep learning methods, character N-gram features, and preprocessing methods. / HaCohen-Kerner, Yaakov; Shayovitz, Elyashiv; Rochman, Shalom et al.
NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop. Association for Computational Linguistics (ACL), 2019. p. 426-430 (NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop).

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

TY - GEN

T1 - JCTDHS at SemEval-2019 task 5

T2 - 13th International Workshop on Semantic Evaluation, SemEval 2019, co-located with the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2019

AU - HaCohen-Kerner, Yaakov

AU - Shayovitz, Elyashiv

AU - Rochman, Shalom

AU - Cahn, Eli

AU - Didi, Gal

AU - Ben-David, Ziv

PY - 2019

Y1 - 2019

N2 - In this paper, we describe our submissions to SemEval-2019 contest. We tackled subtask A - “a binary classification where systems have to predict whether a tweet with a given target (women or immigrants) is hateful or not hateful”, a part of task 5 “Multilingual detection of hate speech against immigrants and women in Twitter (HatEval)”. Our system JCTDHS (Jerusalem College of Technology Detects Hate Speech) was developed for tweets written in English. We applied various supervised ML methods, various combinations of n-gram features using the TF-IDF scheme. In addition, we applied various combinations of eight basic preprocessing methods. Our best submission was a special bidirectional RNN, which was ranked at the 11th position out of 68 submissions.

AB - In this paper, we describe our submissions to SemEval-2019 contest. We tackled subtask A - “a binary classification where systems have to predict whether a tweet with a given target (women or immigrants) is hateful or not hateful”, a part of task 5 “Multilingual detection of hate speech against immigrants and women in Twitter (HatEval)”. Our system JCTDHS (Jerusalem College of Technology Detects Hate Speech) was developed for tweets written in English. We applied various supervised ML methods, various combinations of n-gram features using the TF-IDF scheme. In addition, we applied various combinations of eight basic preprocessing methods. Our best submission was a special bidirectional RNN, which was ranked at the 11th position out of 68 submissions.

UR - http://www.scopus.com/inward/record.url?scp=85118526764&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85118526764

T3 - NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop

SP - 426

EP - 430

BT - NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop

PB - Association for Computational Linguistics (ACL)

Y2 - 6 June 2019 through 7 June 2019

ER -

HaCohen-Kerner Y, Shayovitz E, Rochman S, Cahn E, Didi G, Ben-David Z. JCTDHS at SemEval-2019 task 5: Detection of hate speech in tweets using deep learning methods, character N-gram features, and preprocessing methods. In NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop. Association for Computational Linguistics (ACL). 2019. p. 426-430. (NAACL HLT 2019 - International Workshop on Semantic Evaluation, SemEval 2019, Proceedings of the 13th Workshop).

JCTDHS at SemEval-2019 task 5: Detection of hate speech in tweets using deep learning methods, character N-gram features, and preprocessing methods

Abstract

Publication series

Conference

Bibliographical note

Other files and links

Fingerprint

Cite this