# Overview of Abusive and Threatening Language Detection in Urdu at FIRE 2021

arXiv: https://arxiv.org/abs/2207.06710 · HTML: https://mlsanity.com/paper/2207.06710/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 52 references that are in the map.
- First posted on arXiv 14 Jul 2022.

## Builds on (most cited first, 13 of 13)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Ex Machina: Personal Attacks Seen at Scale](https://mlsanity.com/paper/1610.08914/) (2016)
- [SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)](https://mlsanity.com/paper/1903.08983/) (2019)
- [Directions in Abusive Language Training Data: Garbage In, Garbage Out](https://mlsanity.com/paper/2004.01670/) (2020)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [Understanding Abuse: A Typology of Abusive Language Detection Subtasks](https://mlsanity.com/paper/1705.09899/) (2017)
- [Overview of the HASOC track at FIRE 2020: Hate Speech and Offensive Content Identification in Indo-European Languages](https://mlsanity.com/paper/2108.05927/) (2021)
- [Deep Learning for User Comment Moderation](https://mlsanity.com/paper/1705.09993/) (2017)
- [Graph embeddings for Abusive Language Detection](https://mlsanity.com/paper/2101.02988/) (2021)

## Built on by (most cited first, 5 of 5)

- [Generalists vs. Specialists: Evaluating Large Language Models for Urdu](https://mlsanity.com/paper/2407.04459/) (2024)
- [Large Language Models for Detection of Life-Threatening Texts](https://mlsanity.com/paper/2506.10687/) (2025)
- [HarmPot: An Annotation Framework for Evaluating Offline Harm Potential of Social Media Text](https://mlsanity.com/paper/2403.11108/) (2024)
- [DunbaaBERT: From Sacrifice to Semantics](https://mlsanity.com/paper/2605.26935/) (2026)
- [From Emotion to Expression: Theoretical Foundations and Resources for Fear Speech](https://mlsanity.com/paper/2601.17132/) (2026)

## Abstract (arXiv)

With the growth of social media platform influence, the effect of their misuse becomes more and more impactful. The importance of automatic detection of threatening and abusive language can not be overestimated. However, most of the existing studies and state-of-the-art methods focus on English as the target language, with limited work on low- and medium-resource languages. In this paper, we present two shared tasks of abusive and threatening language detection for the Urdu language which has more than 170 million speakers worldwide. Both are posed as binary classification tasks where participating systems are required to classify tweets in Urdu into two classes, namely: (i) Abusive and Non-Abusive for the first task, and (ii) Threatening and Non-Threatening for the second. We present two manually annotated datasets containing tweets labelled as (i) Abusive and Non-Abusive, and (ii) Threatening and Non-Threatening. The abusive dataset contains 2400 annotated tweets in the train part and 1100 annotated tweets in the test part. The threatening dataset contains 6000 annotated tweets in the train part and 3950 annotated tweets in the test part. We also provide logistic regression and BERT-based baseline classifiers for both tasks. In this shared task, 21 teams from six countries registered for participation (India, Pakistan, China, Malaysia, United Arab Emirates, and Taiwan), 10 teams submitted their runs for Subtask A, which is Abusive Language Detection and 9 teams submitted their runs for Subtask B, which is Threatening Language detection, and seven teams submitted their technical reports. The best performing system achieved an F1-score value of 0.880 for Subtask A and 0.545 for Subtask B. For both subtasks, m-Bert based transformer model showed the best performance.