# Analyzing Hate Speech Data along Racial, Gender and Intersectional Axes

arXiv: https://arxiv.org/abs/2205.06621 · HTML: https://mlsanity.com/paper/2205.06621/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 37 references that are in the map.
- First posted on arXiv 13 May 2022.

## Builds on (most cited first, 15 of 15)

- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://mlsanity.com/paper/1911.03891/) (2019)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [Demographic Dialectal Variation in Social Media: A Case Study of African-American English](https://mlsanity.com/paper/1608.08868/) (2016)
- [Challenges in Automated Debiasing for Toxic Language Detection](https://mlsanity.com/paper/2102.00086/) (2021)
- [Demoting Racial Bias in Hate Speech Detection](https://mlsanity.com/paper/2005.12246/) (2020)
- [Investigating African-American Vernacular English in Transformer-Based Text Generation](https://mlsanity.com/paper/2010.02510/) (2020)
- [Hate Towards the Political Opponent: A Twitter Corpus Study of the 2020 US Elections on the Basis of Offensive Speech and Stance Detection](https://mlsanity.com/paper/2103.01664/) (2021)
- [Intersectional Bias in Hate Speech and Abusive Language Datasets](https://mlsanity.com/paper/2005.05921/) (2020)
- [Towards Equal Gender Representation in the Annotations of Toxic Language Detection](https://mlsanity.com/paper/2106.02183/) (2021)
- [From Toxicity in Online Comments to Incivility in American News: Proceed with Caution](https://mlsanity.com/paper/2102.03671/) (2021)

## Built on by (most cited first, 7 of 7)

- [Measuring Intersectional Biases in Historical Documents](https://mlsanity.com/paper/2305.12376/) (2023)
- [Characterizing Selective Refusal Bias in Large Language Models](https://mlsanity.com/paper/2510.27087/) (2025)
- [Analysis of LLM as a grammatical feature tagger for African American English](https://mlsanity.com/paper/2502.06004/) (2025)
- [Sociocultural knowledge is needed for selection of shots in hate speech detection tasks](https://mlsanity.com/paper/2304.01890/) (2023)
- [Evaluating LLMs for Demographic-Targeted Social Bias Detection: A Comprehensive Benchmark Study](https://mlsanity.com/paper/2510.04641/) (2025)
- [On the Challenges of Building Datasets for Hate Speech Detection](https://mlsanity.com/paper/2309.02912/) (2023)
- [Disentangling Hate Across Target Identities](https://mlsanity.com/paper/2410.10332/) (2024)

## Abstract (arXiv)

To tackle the rising phenomenon of hate speech, efforts have been made towards data curation and analysis. When it comes to analysis of bias, previous work has focused predominantly on race. In our work, we further investigate bias in hate speech datasets along racial, gender and intersectional axes. We identify strong bias against African American English (AAE), masculine and AAE+Masculine tweets, which are annotated as disproportionately more hateful and offensive than from other demographics. We provide evidence that BERT-based models propagate this bias and show that balancing the training data for these protected attributes can lead to fairer models with regards to gender, but not race.