# Challenges in Discriminating Profanity from Hate Speech

arXiv: https://arxiv.org/abs/1803.05495 · HTML: https://mlsanity.com/paper/1803.05495/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Mar 2018.

## Built on by (most cited first, 23 of 23)

- [MUDES: Multilingual Detection of Offensive Spans](https://mlsanity.com/paper/2102.09665/) (2021)
- [A systematic review of Hate Speech automatic detection using Natural Language Processing](https://mlsanity.com/paper/2106.00742/) (2021)
- [Multilingual Offensive Language Identification for Low-resource Languages](https://mlsanity.com/paper/2105.05996/) (2021)
- [Harmful Speech Detection by Language Models Exhibits Gender-Queer Dialect Bias](https://mlsanity.com/paper/2406.00020/) (2024)
- [An Exploratory Analysis of the Relation Between Offensive Language and Mental Health](https://mlsanity.com/paper/2105.14888/) (2021)
- [Hostility Detection in Hindi leveraging Pre-Trained Language Models](https://mlsanity.com/paper/2101.05494/) (2021)
- [WLV-RIT at SemEval-2021 Task 5: A Neural Transformer Framework for Detecting Toxic Spans](https://mlsanity.com/paper/2104.04630/) (2021)
- [Unsupervised Domain Adaptation for Hate Speech Detection Using a Data Augmentation Approach](https://mlsanity.com/paper/2107.12866/) (2021)
- [The State of Profanity Obfuscation in Natural Language Processing](https://mlsanity.com/paper/2210.07595/) (2022)
- [A Federated Learning Approach to Privacy Preserving Offensive Language Identification](https://mlsanity.com/paper/2404.11470/) (2024)
- [A Neighbourhood Framework for Resource-Lean Content Flagging](https://mlsanity.com/paper/2103.17055/) (2021)
- [WLV-RIT at GermEval 2021: Multitask Learning with Transformers to Detect Toxic, Engaging, and Fact-Claiming Comments](https://mlsanity.com/paper/2108.00057/) (2021)
- [Human-in-the-Loop Hate Speech Classification in a Multilingual Context](https://mlsanity.com/paper/2212.02108/) (2022)
- [A Text-to-Text Model for Multilingual Offensive Language Identification](https://mlsanity.com/paper/2312.03379/) (2023)
- [IIITG-ADBU@HASOC-Dravidian-CodeMix-FIRE2020: Offensive Content Detection in Code-Mixed Dravidian Text](https://mlsanity.com/paper/2107.14336/) (2021)
- [TOT: Topology-Aware Optimal Transport For Multimodal Hate Detection](https://mlsanity.com/paper/2303.09314/) (2023)
- [COT: A Generative Approach for Hate Speech Counter-Narratives via Contrastive Optimal Transport](https://mlsanity.com/paper/2406.12304/) (2024)
- [EdgeAIGuard: Agentic LLMs for Minor Protection in Digital Spaces](https://mlsanity.com/paper/2503.00092/) (2025)
- [Domain Classification-based Source-specific Term Penalization for Domain Adaptation in Hate-speech Detection](https://mlsanity.com/paper/2209.08681/) (2022)
- [Transferring Knowledge via Neighborhood-Aware Optimal Transport for Low-Resource Hate Speech Detection](https://mlsanity.com/paper/2210.09340/) (2022)
- [Incorporating Human Explanations for Robust Hate Speech Detection](https://mlsanity.com/paper/2411.06213/) (2024)
- [Evaluating LLMs Capabilities Towards Understanding Social Dynamics](https://mlsanity.com/paper/2411.13008/) (2024)
- [U-GIFT: Uncertainty-Guided Firewall for Toxic Speech in Few-Shot Scenario](https://mlsanity.com/paper/2501.00907/) (2025)

## Abstract (arXiv)

In this study we approach the problem of distinguishing general profanity from hate speech in social media, something which has not been widely considered. Using a new dataset annotated specifically for this task, we employ supervised classification along with a set of features that includes n-grams, skip-grams and clustering-based word representations. We apply approaches based on single classifiers as well as more advanced ensemble classifiers and stacked generalization, achieving the best result of 80% accuracy for this 3-class classification task. Analysis of the results reveals that discriminating hate speech and profanity is not a simple task, which may require features that capture a deeper understanding of the text not always possible with surface n-grams. The variability of gold labels in the annotated data, due to differences in the subjective adjudications of the annotators, is also an issue. Other directions for future work are discussed.