Overview of the HASOC Subtracks at FIRE 2023: Hate Speech and Offensive Content Identification in Assamese, Bengali, Bodo, Gujarati and Sinhala

Tharindu Ranasinghe; Koyel Ghosh; Aditya Shankar Pal; Apurbalal Senapati; Alphaeus Eric Dmonte; Marcos Zampieri; Sandip Modha; Shrey Satapara

doi:10.1145/3632754.3633278

Overview of the HASOC Subtracks at FIRE 2023: Hate Speech and Offensive Content Identification in Assamese, Bengali, Bodo, Gujarati and Sinhala

Tharindu Ranasinghe, Koyel Ghosh, Aditya Shankar Pal, Apurbalal Senapati, Alphaeus Eric Dmonte, Marcos Zampieri, Sandip Modha, Shrey Satapara

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

The evaluation of content moderation systems requires reliable benchmark data. This task becomes particularly formidable for low-resource languages, where obtaining or curating such data poses significant challenges. Addressing this issue, HASOC 2023 organised various shared tasks focused on identifying offensive content in low-resource languages. This paper reports on tasks for hate speech detection in several Indo-Aryan languages—Assamese, Bengali, Gujarati, and Sinhala as well as a Sino-Tibetan language, Bodo, for which limited linguistic resources currently exist. The shared task involved the compilation of multiple datasets. In total, nearly 200 runs were submitted by more than 30 teams, which are presented and analysed in this report.

Original language	English
Title of host publication	FIRE '23: Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation
Editors	Debasis Ganguly, Srijoni Majumdar, Bhaskar Mitra, Parth Gupta, Surupendu Gangopadhyay, Prasenjit Majumder
Publisher	ACM
Pages	13-15
Number of pages	3
ISBN (Electronic)	9798400716324
DOIs	https://doi.org/10.1145/3632754.3633278
Publication status	Published - 12 Feb 2024
Event	FIRE 2023: Forum for Information Retrieval Evaluation - Panjim, India Duration: 15 Dec 2023 → 18 Dec 2023

Publication series

Name	Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation
Publisher	ACM

Conference

Conference	FIRE 2023: Forum for Information Retrieval Evaluation
Country/Territory	India
City	Panjim
Period	15/12/23 → 18/12/23

Keywords

Assamese
Bengali
Bodo
Gujarati
Hate speech
Multilingual Datasets
Sinhala
Social media
Under-resourced languages

Access to Document

10.1145/3632754.3633278

Cite this

Ranasinghe, T., Ghosh, K., Pal, A. S., Senapati, A., Dmonte, A. E., Zampieri, M., Modha, S., & Satapara, S. (2024). Overview of the HASOC Subtracks at FIRE 2023: Hate Speech and Offensive Content Identification in Assamese, Bengali, Bodo, Gujarati and Sinhala. In D. Ganguly, S. Majumdar, B. Mitra, P. Gupta, S. Gangopadhyay, & P. Majumder (Eds.), FIRE '23: Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation (pp. 13-15). (Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation). ACM. https://doi.org/10.1145/3632754.3633278

Ranasinghe, Tharindu ; Ghosh, Koyel ; Pal, Aditya Shankar et al. / Overview of the HASOC Subtracks at FIRE 2023: Hate Speech and Offensive Content Identification in Assamese, Bengali, Bodo, Gujarati and Sinhala. FIRE '23: Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation. editor / Debasis Ganguly ; Srijoni Majumdar ; Bhaskar Mitra ; Parth Gupta ; Surupendu Gangopadhyay ; Prasenjit Majumder. ACM, 2024. pp. 13-15 (Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation).

@inproceedings{35318e52902c4e6b9604db7da85625e9,

title = "Overview of the HASOC Subtracks at FIRE 2023: Hate Speech and Offensive Content Identification in Assamese, Bengali, Bodo, Gujarati and Sinhala",

abstract = "The evaluation of content moderation systems requires reliable benchmark data. This task becomes particularly formidable for low-resource languages, where obtaining or curating such data poses significant challenges. Addressing this issue, HASOC 2023 organised various shared tasks focused on identifying offensive content in low-resource languages. This paper reports on tasks for hate speech detection in several Indo-Aryan languages—Assamese, Bengali, Gujarati, and Sinhala as well as a Sino-Tibetan language, Bodo, for which limited linguistic resources currently exist. The shared task involved the compilation of multiple datasets. In total, nearly 200 runs were submitted by more than 30 teams, which are presented and analysed in this report.",

keywords = "Assamese, Bengali, Bodo, Gujarati, Hate speech, Multilingual Datasets, Sinhala, Social media, Under-resourced languages",

author = "Tharindu Ranasinghe and Koyel Ghosh and Pal, {Aditya Shankar} and Apurbalal Senapati and Dmonte, {Alphaeus Eric} and Marcos Zampieri and Sandip Modha and Shrey Satapara",

year = "2024",

month = feb,

day = "12",

doi = "10.1145/3632754.3633278",

language = "English",

series = "Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation",

publisher = "ACM",

pages = "13--15",

editor = "Debasis Ganguly and Srijoni Majumdar and Bhaskar Mitra and Parth Gupta and Surupendu Gangopadhyay and Majumder, {Prasenjit }",

booktitle = "FIRE '23: Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation",

address = "United States",

note = "FIRE 2023: Forum for Information Retrieval Evaluation ; Conference date: 15-12-2023 Through 18-12-2023",

}

Ranasinghe, T, Ghosh, K, Pal, AS, Senapati, A, Dmonte, AE, Zampieri, M, Modha, S & Satapara, S 2024, Overview of the HASOC Subtracks at FIRE 2023: Hate Speech and Offensive Content Identification in Assamese, Bengali, Bodo, Gujarati and Sinhala. in D Ganguly, S Majumdar, B Mitra, P Gupta, S Gangopadhyay & P Majumder (eds), FIRE '23: Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation. Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation, ACM, pp. 13-15, FIRE 2023: Forum for Information Retrieval Evaluation, Panjim, India, 15/12/23. https://doi.org/10.1145/3632754.3633278

Overview of the HASOC Subtracks at FIRE 2023: Hate Speech and Offensive Content Identification in Assamese, Bengali, Bodo, Gujarati and Sinhala. / Ranasinghe, Tharindu; Ghosh, Koyel; Pal, Aditya Shankar et al.
FIRE '23: Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation. ed. / Debasis Ganguly; Srijoni Majumdar; Bhaskar Mitra; Parth Gupta; Surupendu Gangopadhyay; Prasenjit Majumder. ACM, 2024. p. 13-15 (Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation).

Research output: Chapter in Book/Published conference output › Conference publication

TY - GEN

T1 - Overview of the HASOC Subtracks at FIRE 2023: Hate Speech and Offensive Content Identification in Assamese, Bengali, Bodo, Gujarati and Sinhala

AU - Ranasinghe, Tharindu

AU - Ghosh, Koyel

AU - Pal, Aditya Shankar

AU - Senapati, Apurbalal

AU - Dmonte, Alphaeus Eric

AU - Zampieri, Marcos

AU - Modha, Sandip

AU - Satapara, Shrey

PY - 2024/2/12

Y1 - 2024/2/12

N2 - The evaluation of content moderation systems requires reliable benchmark data. This task becomes particularly formidable for low-resource languages, where obtaining or curating such data poses significant challenges. Addressing this issue, HASOC 2023 organised various shared tasks focused on identifying offensive content in low-resource languages. This paper reports on tasks for hate speech detection in several Indo-Aryan languages—Assamese, Bengali, Gujarati, and Sinhala as well as a Sino-Tibetan language, Bodo, for which limited linguistic resources currently exist. The shared task involved the compilation of multiple datasets. In total, nearly 200 runs were submitted by more than 30 teams, which are presented and analysed in this report.

AB - The evaluation of content moderation systems requires reliable benchmark data. This task becomes particularly formidable for low-resource languages, where obtaining or curating such data poses significant challenges. Addressing this issue, HASOC 2023 organised various shared tasks focused on identifying offensive content in low-resource languages. This paper reports on tasks for hate speech detection in several Indo-Aryan languages—Assamese, Bengali, Gujarati, and Sinhala as well as a Sino-Tibetan language, Bodo, for which limited linguistic resources currently exist. The shared task involved the compilation of multiple datasets. In total, nearly 200 runs were submitted by more than 30 teams, which are presented and analysed in this report.

KW - Assamese

KW - Bengali

KW - Bodo

KW - Gujarati

KW - Hate speech

KW - Multilingual Datasets

KW - Sinhala

KW - Social media

KW - Under-resourced languages

UR - https://dl.acm.org/doi/10.1145/3632754.3633278

UR - http://www.scopus.com/inward/record.url?scp=85180218799&partnerID=8YFLogxK

U2 - 10.1145/3632754.3633278

DO - 10.1145/3632754.3633278

M3 - Conference publication

T3 - Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation

SP - 13

EP - 15

BT - FIRE '23: Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation

A2 - Ganguly, Debasis

A2 - Majumdar, Srijoni

A2 - Mitra, Bhaskar

A2 - Gupta, Parth

A2 - Gangopadhyay, Surupendu

A2 - Majumder, Prasenjit

PB - ACM

T2 - FIRE 2023: Forum for Information Retrieval Evaluation

Y2 - 15 December 2023 through 18 December 2023

ER -

Ranasinghe T, Ghosh K, Pal AS, Senapati A, Dmonte AE, Zampieri M et al. Overview of the HASOC Subtracks at FIRE 2023: Hate Speech and Offensive Content Identification in Assamese, Bengali, Bodo, Gujarati and Sinhala. In Ganguly D, Majumdar S, Mitra B, Gupta P, Gangopadhyay S, Majumder P, editors, FIRE '23: Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation. ACM. 2024. p. 13-15. (Proceedings of the 15th Annual Meeting of the Forum for Information Retrieval Evaluation). Epub 2023 Dec 15. doi: 10.1145/3632754.3633278

Overview of the HASOC Subtracks at FIRE 2023: Hate Speech and Offensive Content Identification in Assamese, Bengali, Bodo, Gujarati and Sinhala

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this