# Beyond Toxic: Toxicity Detection Datasets are Not Enough for Brand Safety

arXiv: https://arxiv.org/abs/2303.15110 · HTML: https://mlsanity.com/paper/2303.15110/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 27 Mar 2023.

## Builds on (most cited first, 11 of 11)

- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [What is the Effect of Importance Weighting in Deep Learning?](https://mlsanity.com/paper/1812.03372/) (2018)
- [Hate Speech Dataset from a White Supremacy Forum](https://mlsanity.com/paper/1809.04444/) (2018)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [Multilingual Offensive Language Identification with Cross-lingual Embeddings](https://mlsanity.com/paper/2010.05324/) (2020)
- [SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification](https://mlsanity.com/paper/2004.14454/) (2020)
- [Towards Hate Speech Detection at Large via Deep Generative Modeling](https://mlsanity.com/paper/2005.06370/) (2020)
- [Exploring Cyberbullying and Other Toxic Behavior in Team Competition Online Games](https://mlsanity.com/paper/1504.02305/) (2015)
- [Generalizing Hate Speech Detection Using Multi-Task Learning: A Case Study of Political Public Figures](https://mlsanity.com/paper/2208.10598/) (2022)
- [Anti-Asian Hate Speech Detection via Data Augmented Semantic Relation Inference](https://mlsanity.com/paper/2204.07010/) (2022)

## Built on by (most cited first, 1 of 1)

- [AI vs. Human Moderators: A Comparative Evaluation of Multimodal LLMs in Content Moderation for Brand Safety](https://mlsanity.com/paper/2508.05527/) (2025)

## Abstract (arXiv)

The rapid growth in user generated content on social media has resulted in a significant rise in demand for automated content moderation. Various methods and frameworks have been proposed for the tasks of hate speech detection and toxic comment classification. In this work, we combine common datasets to extend these tasks to brand safety. Brand safety aims to protect commercial branding by identifying contexts where advertisements should not appear and covers not only toxicity, but also other potentially harmful content. As these datasets contain different label sets, we approach the overall problem as a binary classification task. We demonstrate the need for building brand safety specific datasets via the application of common toxicity detection datasets to a subset of brand safety and empirically analyze the effects of weighted sampling strategies in text classification.