Leveraging Affective Bidirectional Transformers for Offensive Language Detection

AbdelRahim Elmadany, Chiyu Zhang, Muhammad Abdul-Mageed, Azadeh Hashemi


Abstract
Social media are pervasive in our life, making it necessary to ensure safe online experiences by detecting and removing offensive and hate speech. In this work, we report our submission to the Offensive Language and hate-speech Detection shared task organized with the 4th Workshop on Open-Source Arabic Corpora and Processing Tools Arabic (OSACT4). We focus on developing purely deep learning systems, without a need for feature engineering. For that purpose, we develop an effective method for automatic data augmentation and show the utility of training both offensive and hate speech models off (i.e., by fine-tuning) previously trained affective models (i.e., sentiment and emotion). Our best models are significantly better than a vanilla BERT model, with 89.60% acc (82.31% macro F1) for hate speech and 95.20% acc (70.51% macro F1) on official TEST data.
Anthology ID:
2020.osact-1.17
Volume:
Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection
Month:
May
Year:
2020
Address:
Marseille, France
Editors:
Hend Al-Khalifa, Walid Magdy, Kareem Darwish, Tamer Elsayed, Hamdy Mubarak
Venue:
OSACT
SIG:
SIGARAB
Publisher:
European Language Resource Association
Note:
Pages:
102–108
Language:
English
URL:
https://aclanthology.org/2020.osact-1.17
DOI:
Bibkey:
Cite (ACL):
AbdelRahim Elmadany, Chiyu Zhang, Muhammad Abdul-Mageed, and Azadeh Hashemi. 2020. Leveraging Affective Bidirectional Transformers for Offensive Language Detection. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 102–108, Marseille, France. European Language Resource Association.
Cite (Informal):
Leveraging Affective Bidirectional Transformers for Offensive Language Detection (Elmadany et al., OSACT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.osact-1.17.pdf