# Exploring Hate Speech Detection with HateXplain and BERT

arXiv: https://arxiv.org/abs/2208.04489 · HTML: https://mlsanity.com/paper/2208.04489/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 13 references that are in the map.
- First posted on arXiv 9 Aug 2022.

## Builds on (most cited first, 10 of 10)

- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Characterizing and Detecting Hateful Users on Twitter](https://mlsanity.com/paper/1803.08977/) (2018)
- [MUDES: Multilingual Detection of Offensive Spans](https://mlsanity.com/paper/2102.09665/) (2021)
- [WLV-RIT at SemEval-2021 Task 5: A Neural Transformer Framework for Detecting Toxic Spans](https://mlsanity.com/paper/2104.04630/) (2021)
- [Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic](https://mlsanity.com/paper/2104.03506/) (2021)
- [How Hateful are Movies? A Study and Prediction on Movie Subtitles](https://mlsanity.com/paper/2108.10724/) (2021)

## Built on by (most cited first, 2 of 2)

- [Perplexed by Quality: A Perplexity-based Method for Adult and Harmful Content Detection in Multilingual Heterogeneous Web Data](https://mlsanity.com/paper/2212.10440/) (2022)
- [Rethinking Multimodal Content Moderation from an Asymmetric Angle with Mixed-modality](https://mlsanity.com/paper/2305.10547/) (2023)

## Abstract (arXiv)

Hate Speech takes many forms to target communities with derogatory comments, and takes humanity a step back in societal progress. HateXplain is a recently published and first dataset to use annotated spans in the form of rationales, along with speech classification categories and targeted communities to make the classification more humanlike, explainable, accurate and less biased. We tune BERT to perform this task in the form of rationales and class prediction, and compare our performance on different metrics spanning across accuracy, explainability and bias. Our novelty is threefold. Firstly, we experiment with the amalgamated rationale class loss with different importance values. Secondly, we experiment extensively with the ground truth attention values for the rationales. With the introduction of conservative and lenient attentions, we compare performance of the model on HateXplain and test our hypothesis. Thirdly, in order to improve the unintended bias in our models, we use masking of the target community words and note the improvement in bias and explainability metrics. Overall, we are successful in achieving model explanability, bias removal and several incremental improvements on the original BERT implementation.