# Generalizing Hate Speech Detection Using Multi-Task Learning: A Case Study of Political Public Figures

arXiv: https://arxiv.org/abs/2208.10598 · HTML: https://mlsanity.com/paper/2208.10598/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 53 references that are in the map.
- First posted on arXiv 22 Aug 2022.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Hate Speech Dataset from a White Supremacy Forum](https://mlsanity.com/paper/1809.04444/) (2018)
- [Deep Learning for Hate Speech Detection in Tweets](https://mlsanity.com/paper/1706.00188/) (2017)
- [A Benchmark Dataset for Learning to Intervene in Online Hate Speech](https://mlsanity.com/paper/1909.04251/) (2019)
- [A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media](https://mlsanity.com/paper/1910.12574/) (2019)
- [Detecting Online Hate Speech Using Context Aware Models](https://mlsanity.com/paper/1710.07395/) (2017)
- [Towards generalisable hate speech detection: a review on obstacles and solutions](https://mlsanity.com/paper/2102.08886/) (2021)
- [Deep Learning for Detecting Cyberbullying Across Multiple Social Media Platforms](https://mlsanity.com/paper/1801.06482/) (2018)
- [Hate Speech Detection: A Solved Problem? The Challenging Case of Long Tail on Twitter](https://mlsanity.com/paper/1803.03662/) (2018)
- [Peer to Peer Hate: Hate Speech Instigators and Their Targets](https://mlsanity.com/paper/1804.04649/) (2018)
- [Transfer Learning for Hate Speech Detection in Social Media](https://mlsanity.com/paper/1906.03829/) (2019)
- [Slipping to the Extreme: A Mixed Method to Explain How Extreme Opinions Infiltrate Online Discussions](https://mlsanity.com/paper/2109.00302/) (2021)
- [Estimating Attention Flow in Online Video Networks](https://mlsanity.com/paper/1908.07123/) (2019)
- [Variation across Scales: Measurement Fidelity under Twitter Data Sampling](https://mlsanity.com/paper/2003.09557/) (2020)
- [Evolution of Privacy Loss in Wikipedia](https://mlsanity.com/paper/1512.03523/) (2015)

## Built on by (most cited first, 10 of 10)

- [Mario at EXIST 2025: A Simple Gateway to Effective Multilingual Sexism Detection](https://mlsanity.com/paper/2507.10996/) (2025)
- [X-Troll: eXplainable Detection of State-Sponsored Information Operations Agents](https://mlsanity.com/paper/2508.16021/) (2025)
- [Beyond Toxic: Toxicity Detection Datasets are Not Enough for Brand Safety](https://mlsanity.com/paper/2303.15110/) (2023)
- [Studying Socially Unacceptable Discourse Classification (SUD) through different eyes: "Are we on the same page ?"](https://mlsanity.com/paper/2308.04180/) (2023)
- [DoDo Learning: DOmain-DemOgraphic Transfer in Language Models for Detecting Abuse Targeted at Public Figures](https://mlsanity.com/paper/2307.16811/) (2023)
- [Analysis of Socially Unacceptable Discourse with Zero-shot Learning](https://mlsanity.com/paper/2409.13735/) (2024)
- [VocalTweets: Investigating Social Media Offensive Language Among Nigerian Musicians](https://mlsanity.com/paper/2411.06477/) (2024)
- [Exploration and Evaluation of Bias in Cyberbullying Detection with Machine Learning](https://mlsanity.com/paper/2412.00609/) (2024)
- [Survey Transfer Learning: Recycling Data with Silicon Responses](https://mlsanity.com/paper/2501.06577/) (2025)
- [Web(er) of Hate: A Survey on How Hate Speech Is Typed](https://mlsanity.com/paper/2506.16190/) (2025)

## Abstract (arXiv)

Automatic identification of hateful and abusive content is vital in combating the spread of harmful online content and its damaging effects. Most existing works evaluate models by examining the generalization error on train-test splits on hate speech datasets. These datasets often differ in their definitions and labeling criteria, leading to poor generalization performance when predicting across new domains and datasets. This work proposes a new Multi-task Learning (MTL) pipeline that trains simultaneously across multiple hate speech datasets to construct a more encompassing classification model. Using a dataset-level leave-one-out evaluation (designating a dataset for testing and jointly training on all others), we trial the MTL detection on new, previously unseen datasets. Our results consistently outperform a large sample of existing work. We show strong results when examining the generalization error in train-test splits and substantial improvements when predicting on previously unseen datasets. Furthermore, we assemble a novel dataset, dubbed PubFigs, focusing on the problematic speech of American Public Political Figures. We crowdsource-label using Amazon MTurk more than 20,000 tweets and machine-label problematic speech in all the 305,235 tweets in PubFigs. We find that the abusive and hate tweeting mainly originates from right-leaning figures and relates to six topics, including Islam, women, ethnicity, and immigrants. We show that MTL builds embeddings that can simultaneously separate abusive from hate speech, and identify its topics.