# Tackling Racial Bias in Automated Online Hate Detection: Towards Fair and Accurate Classification of Hateful Online Users Using Geometric Deep Learning

arXiv: https://arxiv.org/abs/2103.11806 · HTML: https://mlsanity.com/paper/2103.11806/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 57 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 20 of 20)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Inherent Trade-Offs in the Fair Determination of Risk Scores](https://mlsanity.com/paper/1609.05807/) (2016)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [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)
- [A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media](https://mlsanity.com/paper/1910.12574/) (2019)
- [Characterizing and Detecting Hateful Users on Twitter](https://mlsanity.com/paper/1803.08977/) (2018)
- [Detecting East Asian Prejudice on Social Media](https://mlsanity.com/paper/2005.03909/) (2020)
- [Mean Birds: Detecting Aggression and Bullying on Twitter](https://mlsanity.com/paper/1702.06877/) (2017)
- [Leveraging Intra-User and Inter-User Representation Learning for Automated Hate Speech Detection](https://mlsanity.com/paper/1804.03124/) (2018)
- [Demographic Inference and Representative Population Estimates from Multilingual Social Media Data](https://mlsanity.com/paper/1905.05961/) (2019)
- [Abusive Language Detection with Graph Convolutional Networks](https://mlsanity.com/paper/1904.04073/) (2019)
- [Detecting weak and strong Islamophobic hate speech on social media](https://mlsanity.com/paper/1812.10400/) (2018)
- [Online networks and subjective well-being](https://mlsanity.com/paper/1408.3550/) (2014)

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

- [Hate Speech Classifiers Learn Human-Like Social Stereotypes](https://mlsanity.com/paper/2110.14839/) (2021)

## Abstract (arXiv)

Online hate is a growing concern on many social media platforms and other sites. To combat it, technology companies are increasingly identifying and sanctioning `hateful users' rather than simply moderating hateful content. Yet, most research in online hate detection to date has focused on hateful content. This paper examines how fairer and more accurate hateful user detection systems can be developed by incorporating social network information through geometric deep learning. Geometric deep learning dynamically learns information-rich network representations and can generalise to unseen nodes. This is essential for moving beyond manually engineered network features, which lack scalability and produce information-sparse network representations. This paper compares the accuracy of geometric deep learning with other techniques which either exclude network information or incorporate it through manual feature engineering (e.g., node2vec). It also evaluates the fairness of these techniques using the `predictive equality' criteria, comparing the false positive rates on a subset of 136 African-American users with 4836 other users. Geometric deep learning produces the most accurate and fairest classifier, with an AUC score of 90.8% on the entire dataset and a false positive rate of zero among the African-American subset for the best performing model. This highlights the benefits of more effectively incorporating social network features in automated hateful user detection. Such an approach is also easily operationalized for real-world content moderation as it has an efficient and scalable design.