A Comparative Study of Different State-of-the-Art Hate Speech Detection Methods in Hindi-English Code-Mixed Data

Priya Rani; Suryawanshi Suryawanshi; Koustava Goswami; Bharathi Raja Chakravarthi; Theodorus Fransen; John Philip McCrae

doi:10.13025/21328

A Comparative Study of Different State-of-the-Art Hate Speech Detection Methods in Hindi-English Code-Mixed Data

Priya Rani
, Suryawanshi Suryawanshi
, Koustava Goswami
, Bharathi Raja Chakravarthi
, Theodorus Fransen
, John Philip McCrae

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

2 Downloads (Pure)

Abstract

Hate speech detection in social media communication has become one of the primary concerns to avoid conflicts and curb undesired activities. In an environment where multilingual speakers switch among multiple languages, hate speech detection becomes a challenging task using methods that are designed for monolingual corpora. In our work, we attempt to analyze, detect and provide a comparative study of hate speech in a code-mixed social media text. We also provide a Hindi-English code-mixed data set consisting of Facebook and Twitter posts and comments. Our experiments show that deep learning models trained on this code-mixed corpus perform better.

Original language	English (Ireland)
Title of host publication	Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying
Place of Publication	Marseille, France
Publisher	European Language Resources Association (ELRA)
DOIs	https://doi.org/10.13025/21328
Publication status	Published - 1 May 2020

Keywords

Code mixing
Convolutional Neural Networks
Data Science Institute

Access to Document

10.13025/21328Licence: CC BY-NC-ND

2020Accepted author manuscript, 285 KBLicence: CC BY-NC-ND

Cite this

Rani, P., Suryawanshi, S., Goswami, K., Chakravarthi, B. R., Fransen, T., & McCrae, J. P. (2020). A Comparative Study of Different State-of-the-Art Hate Speech Detection Methods in Hindi-English Code-Mixed Data. In Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying European Language Resources Association (ELRA). https://doi.org/10.13025/21328

@inproceedings{354a017eb5de49f29db8871b213a36ef,

title = "A Comparative Study of Different State-of-the-Art Hate Speech Detection Methods in Hindi-English Code-Mixed Data",

abstract = "Hate speech detection in social media communication has become one of the primary concerns to avoid conflicts and curb undesired activities. In an environment where multilingual speakers switch among multiple languages, hate speech detection becomes a challenging task using methods that are designed for monolingual corpora. In our work, we attempt to analyze, detect and provide a comparative study of hate speech in a code-mixed social media text. We also provide a Hindi-English code-mixed data set consisting of Facebook and Twitter posts and comments. Our experiments show that deep learning models trained on this code-mixed corpus perform better.",

keywords = "Code mixing, Convolutional Neural Networks, Data Science Institute",

author = "Priya Rani and Suryawanshi Suryawanshi and Koustava Goswami and Chakravarthi, \{Bharathi Raja\} and Theodorus Fransen and McCrae, \{John Philip\}",

year = "2020",

month = may,

day = "1",

doi = "10.13025/21328",

language = "English (Ireland)",

booktitle = "Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying",

publisher = "European Language Resources Association (ELRA)",

}

Rani, P, Suryawanshi, S, Goswami, K, Chakravarthi, BR, Fransen, T & McCrae, JP 2020, A Comparative Study of Different State-of-the-Art Hate Speech Detection Methods in Hindi-English Code-Mixed Data. in Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying. European Language Resources Association (ELRA), Marseille, France. https://doi.org/10.13025/21328

A Comparative Study of Different State-of-the-Art Hate Speech Detection Methods in Hindi-English Code-Mixed Data. / Rani, Priya; Suryawanshi, Suryawanshi; Goswami, Koustava et al.
Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying. Marseille, France: European Language Resources Association (ELRA), 2020.

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

TY - GEN

T1 - A Comparative Study of Different State-of-the-Art Hate Speech Detection Methods in Hindi-English Code-Mixed Data

AU - Rani, Priya

AU - Suryawanshi, Suryawanshi

AU - Goswami, Koustava

AU - Chakravarthi, Bharathi Raja

AU - Fransen, Theodorus

AU - McCrae, John Philip

PY - 2020/5/1

Y1 - 2020/5/1

N2 - Hate speech detection in social media communication has become one of the primary concerns to avoid conflicts and curb undesired activities. In an environment where multilingual speakers switch among multiple languages, hate speech detection becomes a challenging task using methods that are designed for monolingual corpora. In our work, we attempt to analyze, detect and provide a comparative study of hate speech in a code-mixed social media text. We also provide a Hindi-English code-mixed data set consisting of Facebook and Twitter posts and comments. Our experiments show that deep learning models trained on this code-mixed corpus perform better.

AB - Hate speech detection in social media communication has become one of the primary concerns to avoid conflicts and curb undesired activities. In an environment where multilingual speakers switch among multiple languages, hate speech detection becomes a challenging task using methods that are designed for monolingual corpora. In our work, we attempt to analyze, detect and provide a comparative study of hate speech in a code-mixed social media text. We also provide a Hindi-English code-mixed data set consisting of Facebook and Twitter posts and comments. Our experiments show that deep learning models trained on this code-mixed corpus perform better.

KW - Code mixing

KW - Convolutional Neural Networks

KW - Data Science Institute

UR - http://hdl.handle.net/10379/16085

U2 - 10.13025/21328

DO - 10.13025/21328

M3 - Conference Publication

BT - Proceedings of the Second Workshop on Trolling, Aggression and Cyberbullying

PB - European Language Resources Association (ELRA)

CY - Marseille, France

ER -

A Comparative Study of Different State-of-the-Art Hate Speech Detection Methods in Hindi-English Code-Mixed Data

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this