University of Oulu

Jahan, M. S., Beddiar, D. R., Oussalah, M., Arhab, N., & Bounab, Y. (2021). Hate and Offensive language detection using BERT for English Subtask A. In P. Mehta, T. Mandl, P. Majumder, & Mandar M. (Eds.), Working Notes of FIRE 2021 - Forum for Information Retrieval Evaluation, Gandhinagar, India, December 13-17, 2021 (pp. 262-272). RWTH Aachen University.

Hate and offensive language detection using BERT for English subtask A

Saved in:
Author: Jahan, Md Saroar1; Beddiar, Djamila Romaissa1; Oussalah, Mourad1;
Organizations: 1University of Oulu, Faculty of Information Tech., CMVS, PO Box 4500, Oulu 90014, FINLAND
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 0.7 MB)
Persistent link:
Language: English
Published: RWTH Aachen University, 2021
Publish Date: 2022-07-05


This paper presents the results and main findings of the HASOC-2021 Hate/Offensive Language Identification Subtask A. The work consisted of fine-tuning pre-trained transformer networks such as BERT and an ensemble of different models, including CNN and BERT. We have used the HASOC-2021 English 3.8k annotated twitter dataset. We compare current pre-trained transformer networks with and without Masked-Language-Modelling (MLM) fine-tuning on their performance for offensive language detection. Among different BERT MLM fine-tuned BERT-base, BERT-large, and ALBERT outperformed other models; however, BERT and CNN ensemble classifier that applies majority voting outperformed other models, achieving 85.1% F1 score on both hate/non-hate labels. Our final submission achieved 77.0 F1 in the HASOC-2021 competition.

see all

Series: CEUR workshop proceedings
ISSN: 1613-0073
ISSN-E: 1613-0073
ISSN-L: 1613-0073
Volume: 3159
Pages: 262 - 272
Host publication: Working Notes of FIRE 2021 - Forum for Information Retrieval Evaluation, Gandhinagar, India, December 13-17, 2021
Host publication editor: Mehta, Parth
Mandl, Thomas
Majumder, Prasenjit
Mitra, Mandar
Conference: Forum for Information Retrieval Evaluation
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Funding: This project was partially funded by EU Project WaterLine (Downscaling Remotely Sensed Products to Improve Hydrological Modelling Performance), and EU Project YoungRes (#823701), which are gratefully acknowledged.
Copyright information: © 2021 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).