# Leveraging Affective Bidirectional Transformers for Offensive Language Detection

arXiv: https://arxiv.org/abs/2006.01266 · HTML: https://mlsanity.com/paper/2006.01266/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2020.

## Built on by (most cited first, 11 of 11)

- [NADI 2022: The Third Nuanced Arabic Dialect Identification Shared Task](https://mlsanity.com/paper/2210.09582/) (2022)
- [Multi-Task Learning with Sentiment, Emotion, and Target Detection to Recognize Hate Speech and Offensive Language](https://mlsanity.com/paper/2109.10255/) (2021)
- [Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Bias](https://mlsanity.com/paper/2204.10365/) (2022)
- [TweetBLM: A Hate Speech Dataset and Analysis of Black Lives Matter-related Microblogs on Twitter](https://mlsanity.com/paper/2108.12521/) (2021)
- [Transfer Learning Approach for Arabic Offensive Language Detection System -- BERT-Based Model](https://mlsanity.com/paper/2102.05708/) (2021)
- [A Benchmark Study of Contrastive Learning for Arabic Social Meaning](https://mlsanity.com/paper/2210.12314/) (2022)
- [Don't Erase, Inform! Detecting and Contextualizing Harmful Language in Cultural Heritage Collections](https://mlsanity.com/paper/2505.24538/) (2025)
- [Fine-Tuning Approach for Arabic Offensive Language Detection System: BERT-Based Model](https://mlsanity.com/paper/2203.03542/) (2022)
- [Ensemble of pre-trained language models and data augmentation for hate speech detection from Arabic tweets](https://mlsanity.com/paper/2407.02448/) (2024)
- [Multi-task Learning with Active Learning for Arabic Offensive Speech Detection](https://mlsanity.com/paper/2506.02753/) (2025)
- [Explain the Flag: Contextualizing Hate Speech Beyond Censorship](https://mlsanity.com/paper/2604.14970/) (2026)

## Abstract (arXiv)

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.