# Understanding and Detecting Dangerous Speech in Social Media

arXiv: https://arxiv.org/abs/2005.06608 · HTML: https://mlsanity.com/paper/2005.06608/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2020.

## Built on by (most cited first, 12 of 12)

- [ORCA: A Challenging Benchmark for Arabic Language Understanding](https://mlsanity.com/paper/2212.10758/) (2022)
- [GPTAraEval: A Comprehensive Evaluation of ChatGPT on Arabic NLP](https://mlsanity.com/paper/2305.14976/) (2023)
- [Arabic Dataset for LLM Safeguard Evaluation](https://mlsanity.com/paper/2410.17040/) (2024)
- [JASMINE: Arabic GPT Models for Few-Shot Learning](https://mlsanity.com/paper/2212.10755/) (2022)
- [Self-Training Pre-Trained Language Models for Zero- and Few-Shot Multi-Dialectal Arabic Sequence Labeling](https://mlsanity.com/paper/2101.04758/) (2021)
- [Abusive and Threatening Language Detection in Urdu using Boosting based and BERT based models: A Comparative Approach](https://mlsanity.com/paper/2111.14830/) (2021)
- [MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMs](https://mlsanity.com/paper/2505.19800/) (2025)
- [The Skipped Beat: A Study of Sociopragmatic Understanding in LLMs for 64 Languages](https://mlsanity.com/paper/2310.14557/) (2023)
- [Toxic language detection: a systematic review of Arabic datasets](https://mlsanity.com/paper/2312.07228/) (2023)
- [A Benchmark Study of Contrastive Learning for Arabic Social Meaning](https://mlsanity.com/paper/2210.12314/) (2022)
- [On the importance of Data Scale in Pretraining Arabic Language Models](https://mlsanity.com/paper/2401.07760/) (2024)
- [Posts of Peril: Detecting Information About Hazards in Text](https://mlsanity.com/paper/2405.17838/) (2024)

## Abstract (arXiv)

Social media communication has become a significant part of daily activity in modern societies. For this reason, ensuring safety in social media platforms is a necessity. Use of dangerous language such as physical threats in online environments is a somewhat rare, yet remains highly important. Although several works have been performed on the related issue of detecting offensive and hateful language, dangerous speech has not previously been treated in any significant way. Motivated by these observations, we report our efforts to build a labeled dataset for dangerous speech. We also exploit our dataset to develop highly effective models to detect dangerous content. Our best model performs at 59.60% macro F1, significantly outperforming a competitive baseline.