# Machine Learning Suites for Online Toxicity Detection

arXiv: https://arxiv.org/abs/1810.01869 · HTML: https://mlsanity.com/paper/1810.01869/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Oct 2018.

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

- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [COLD: A Benchmark for Chinese Offensive Language Detection](https://mlsanity.com/paper/2201.06025/) (2022)
- [Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models](https://mlsanity.com/paper/2307.09209/) (2023)
- [Identification of Bias Against People with Disabilities in Sentiment Analysis and Toxicity Detection Models](https://mlsanity.com/paper/2111.13259/) (2021)
- [Countering Online Hate Speech: An NLP Perspective](https://mlsanity.com/paper/2109.02941/) (2021)
- [Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content](https://mlsanity.com/paper/2308.13768/) (2023)
- [Offensive Language Identification in Low-resourced Code-mixed Dravidian languages using Pseudo-labeling](https://mlsanity.com/paper/2108.12177/) (2021)
- [BERT-Beta: A Proactive Probabilistic Approach to Text Moderation](https://mlsanity.com/paper/2109.08805/) (2021)
- [UoB at SemEval-2021 Task 5: Extending Pre-Trained Language Models to Include Task and Domain-Specific Information for Toxic Span Prediction](https://mlsanity.com/paper/2110.03730/) (2021)
- [Effect of Toxic Review Content on Overall Product Sentiment](https://mlsanity.com/paper/2201.02857/) (2022)
- [Learning to love diligent trolls: Accounting for rater effects in the dialogue safety task](https://mlsanity.com/paper/2310.19271/) (2023)
- [Soft Weighted Machine Unlearning](https://mlsanity.com/paper/2505.18783/) (2025)

## Abstract (arXiv)

To identify and classify toxic online commentary, the modern tools of data science transform raw text into key features from which either thresholding or learning algorithms can make predictions for monitoring offensive conversations. We systematically evaluate 62 classifiers representing 19 major algorithmic families against features extracted from the Jigsaw dataset of Wikipedia comments. We compare the classifiers based on statistically significant differences in accuracy and relative execution time. Among these classifiers for identifying toxic comments, tree-based algorithms provide the most transparently explainable rules and rank-order the predictive contribution of each feature. Among 28 features of syntax, sentiment, emotion and outlier word dictionaries, a simple bad word list proves most predictive of offensive commentary.