Home > Research > Publications & Outputs > Towards Generalized Offensive Language Identifi...

Electronic data

  • 2407.18738v1

    Accepted author manuscript, 482 KB, PDF document

View graph of relations

Towards Generalized Offensive Language Identification

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

E-pub ahead of print

Standard

Towards Generalized Offensive Language Identification. / Dmonte, Alphaeus ; Arya, Tejas ; Ranasinghe, Tharindu et al.
Proceedings of the the 16th International Conference on Advances in Social Networks Analysis and Mining. Cham: Springer Nature, 2024.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Dmonte, A, Arya, T, Ranasinghe, T & Zampieri, M 2024, Towards Generalized Offensive Language Identification. in Proceedings of the the 16th International Conference on Advances in Social Networks Analysis and Mining. Springer Nature, Cham, The 16th International Conference on Advances in Social Networks Analysis and Mining, Calabria, Italy, 2/09/24.

APA

Dmonte, A., Arya, T., Ranasinghe, T., & Zampieri, M. (2024). Towards Generalized Offensive Language Identification. In Proceedings of the the 16th International Conference on Advances in Social Networks Analysis and Mining Springer Nature. Advance online publication.

Vancouver

Dmonte A, Arya T, Ranasinghe T, Zampieri M. Towards Generalized Offensive Language Identification. In Proceedings of the the 16th International Conference on Advances in Social Networks Analysis and Mining. Cham: Springer Nature. 2024 Epub 2024 Sept 5.

Author

Dmonte, Alphaeus ; Arya, Tejas ; Ranasinghe, Tharindu et al. / Towards Generalized Offensive Language Identification. Proceedings of the the 16th International Conference on Advances in Social Networks Analysis and Mining. Cham : Springer Nature, 2024.

Bibtex

@inproceedings{574791820bed480589c949bb13e5c018,
title = "Towards Generalized Offensive Language Identification",
abstract = "The prevalence of offensive content on the internet, encompassing hate speech and cyberbullying, is a pervasive issue worldwide. Consequently, it has garnered significant attention from the machine learning (ML) and natural language processing (NLP) communities. As a result, numerous systems have been developed to automatically identify potentially harmful content and mitigate its impact. These systems can follow two approaches; (1) Use publicly available models and application endpoints, including prompting large language models (LLMs) (2) Annotate datasets and train ML models on them. However, both approaches lack an understanding of how generalizable they are. Furthermore, the applicability of these systems is often questioned in off-domain and practical environments. This paper empirically evaluates the generalizability of offensive language detection models and datasets across a novel generalized benchmark. We answer three research questions on generalizability. Our findings will be useful in creating robust real-world offensive language detection systems.",
author = "Alphaeus Dmonte and Tejas Arya and Tharindu Ranasinghe and Marcos Zampieri",
year = "2024",
month = sep,
day = "5",
language = "English",
booktitle = "Proceedings of the the 16th International Conference on Advances in Social Networks Analysis and Mining",
publisher = "Springer Nature",
note = "The 16th International Conference on Advances in Social Networks Analysis and Mining, ASONAM-2024 ; Conference date: 02-09-2024 Through 05-09-2024",
url = "https://asonam.cpsc.ucalgary.ca/2024/",

}

RIS

TY - GEN

T1 - Towards Generalized Offensive Language Identification

AU - Dmonte, Alphaeus

AU - Arya, Tejas

AU - Ranasinghe, Tharindu

AU - Zampieri, Marcos

PY - 2024/9/5

Y1 - 2024/9/5

N2 - The prevalence of offensive content on the internet, encompassing hate speech and cyberbullying, is a pervasive issue worldwide. Consequently, it has garnered significant attention from the machine learning (ML) and natural language processing (NLP) communities. As a result, numerous systems have been developed to automatically identify potentially harmful content and mitigate its impact. These systems can follow two approaches; (1) Use publicly available models and application endpoints, including prompting large language models (LLMs) (2) Annotate datasets and train ML models on them. However, both approaches lack an understanding of how generalizable they are. Furthermore, the applicability of these systems is often questioned in off-domain and practical environments. This paper empirically evaluates the generalizability of offensive language detection models and datasets across a novel generalized benchmark. We answer three research questions on generalizability. Our findings will be useful in creating robust real-world offensive language detection systems.

AB - The prevalence of offensive content on the internet, encompassing hate speech and cyberbullying, is a pervasive issue worldwide. Consequently, it has garnered significant attention from the machine learning (ML) and natural language processing (NLP) communities. As a result, numerous systems have been developed to automatically identify potentially harmful content and mitigate its impact. These systems can follow two approaches; (1) Use publicly available models and application endpoints, including prompting large language models (LLMs) (2) Annotate datasets and train ML models on them. However, both approaches lack an understanding of how generalizable they are. Furthermore, the applicability of these systems is often questioned in off-domain and practical environments. This paper empirically evaluates the generalizability of offensive language detection models and datasets across a novel generalized benchmark. We answer three research questions on generalizability. Our findings will be useful in creating robust real-world offensive language detection systems.

M3 - Conference contribution/Paper

BT - Proceedings of the the 16th International Conference on Advances in Social Networks Analysis and Mining

PB - Springer Nature

CY - Cham

T2 - The 16th International Conference on Advances in Social Networks Analysis and Mining

Y2 - 2 September 2024 through 5 September 2024

ER -