Next Article in Journal
Computer Vision and Machine Learning for Tuna and Salmon Meat Classification
Next Article in Special Issue
Literature Review of Deep Network Compression
Previous Article in Journal
Identifying Benchmarks for Failure Prediction in Industry 4.0
Previous Article in Special Issue
Convolutional Extreme Learning Machines: A Systematic Review
Article

Arabic Offensive and Hate Speech Detection Using a Cross-Corpora Multi-Task Learning Model

1
Department of Mathematics and Computer Science, Faculty of Science and Technology, University of Ahmed DRAIA, Adrar 01000, Algeria
2
LDDI Laboratory, Faculty of Science and Technology, University of Ahmed DRAIA, Adrar 01000, Algeria
3
State Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
4
Department of Mathematics, Faculty of Science, Zagazig University, Zagazig 44519, Egypt
5
Department of Computer and Systems Engineering, Faculty of Engineering, Zagazig University, Zagazig 44519, Egypt
6
Faculty of Applied Mathematics, Silesian University of Technology, 44-100 Gliwice, Poland
*
Authors to whom correspondence should be addressed.
These authors contributed equally to this work.
Academic Editor: Antony Bryant
Received: 26 August 2021 / Revised: 3 October 2021 / Accepted: 3 October 2021 / Published: 8 October 2021
(This article belongs to the Special Issue Feature Paper in Informatics)
As social media platforms offer a medium for opinion expression, social phenomena such as hatred, offensive language, racism, and all forms of verbal violence have increased spectacularly. These behaviors do not affect specific countries, groups, or communities only, extending beyond these areas into people’s everyday lives. This study investigates offensive and hate speech on Arab social media to build an accurate offensive and hate speech detection system. More precisely, we develop a classification system for determining offensive and hate speech using a multi-task learning (MTL) model built on top of a pre-trained Arabic language model. We train the MTL model on the same task using cross-corpora representing a variation in the offensive and hate context to learn global and dataset-specific contextual representations. The developed MTL model showed a significant performance and outperformed existing models in the literature on three out of four datasets for Arabic offensive and hate speech detection tasks. View Full-Text
Keywords: multi-task learning; Arabic language model; contextual representations; offensive language; hate speech multi-task learning; Arabic language model; contextual representations; offensive language; hate speech
Show Figures

Figure 1

MDPI and ACS Style

Aldjanabi, W.; Dahou, A.; Al-qaness, M.A.A.; Elaziz, M.A.; Helmi, A.M.; Damaševičius, R. Arabic Offensive and Hate Speech Detection Using a Cross-Corpora Multi-Task Learning Model. Informatics 2021, 8, 69. https://0-doi-org.brum.beds.ac.uk/10.3390/informatics8040069

AMA Style

Aldjanabi W, Dahou A, Al-qaness MAA, Elaziz MA, Helmi AM, Damaševičius R. Arabic Offensive and Hate Speech Detection Using a Cross-Corpora Multi-Task Learning Model. Informatics. 2021; 8(4):69. https://0-doi-org.brum.beds.ac.uk/10.3390/informatics8040069

Chicago/Turabian Style

Aldjanabi, Wassen, Abdelghani Dahou, Mohammed A.A. Al-qaness, Mohamed A. Elaziz, Ahmed M. Helmi, and Robertas Damaševičius. 2021. "Arabic Offensive and Hate Speech Detection Using a Cross-Corpora Multi-Task Learning Model" Informatics 8, no. 4: 69. https://0-doi-org.brum.beds.ac.uk/10.3390/informatics8040069

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop