# Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement

arXiv: https://arxiv.org/abs/2404.11036 · HTML: https://mlsanity.com/paper/2404.11036/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 47 references that are in the map.
- First posted on arXiv 17 Apr 2024.

## Builds on (most cited first, 26 of 26)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Regularizing Neural Networks by Penalizing Confident Output Distributions](https://mlsanity.com/paper/1701.06548/) (2017)
- [HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection](https://mlsanity.com/paper/2012.10289/) (2020)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [HateBERT: Retraining BERT for Abusive Language Detection in English](https://mlsanity.com/paper/2010.12472/) (2020)
- [Invariance, Causality and Robustness](https://mlsanity.com/paper/1812.08233/) (2018)
- [Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations](https://mlsanity.com/paper/2306.04618/) (2023)
- [Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach](https://mlsanity.com/paper/2010.07835/) (2020)
- [A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation](https://mlsanity.com/paper/2010.14766/) (2020)
- [Co-learning: Learning from Noisy Labels with Self-supervision](https://mlsanity.com/paper/2108.04063/) (2021)
- [X-Class: Text Classification with Extremely Weak Supervision](https://mlsanity.com/paper/2010.12794/) (2020)
- [Disentangling Hate in Online Memes](https://mlsanity.com/paper/2108.06207/) (2021)
- [Denoising Multi-Source Weak Supervision for Neural Text Classification](https://mlsanity.com/paper/2010.04582/) (2020)
- [Racism is a Virus: Anti-Asian Hate and Counterspeech in Social Media during the COVID-19 Crisis](https://mlsanity.com/paper/2005.12423/) (2020)
- [Text Classification Using Label Names Only: A Language Model Self-Training Approach](https://mlsanity.com/paper/2010.07245/) (2020)
- [Towards Interpretable Hate Speech Detection using Large Language Model-extracted Rationales](https://mlsanity.com/paper/2403.12403/) (2024)
- [AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detection](https://mlsanity.com/paper/2212.10405/) (2022)
- [Causality Guided Disentanglement for Cross-Platform Hate Speech Detection](https://mlsanity.com/paper/2308.02080/) (2023)
- [PEACE: Cross-Platform Hate Speech Detection- A Causality-guided Framework](https://mlsanity.com/paper/2306.08804/) (2023)
- [SepLL: Separating Latent Class Labels from Weak Supervision Noise](https://mlsanity.com/paper/2210.13898/) (2022)
- [Exploring Platform Migration Patterns between Twitter and Mastodon: A User Behavior Study](https://mlsanity.com/paper/2305.09196/) (2023)
- [Harnessing Artificial Intelligence to Combat Online Hate: Exploring the Challenges and Opportunities of Large Language Models in Hate Speech Detection](https://mlsanity.com/paper/2403.08035/) (2024)
- [Towards Weakly-Supervised Hate Speech Classification Across Datasets](https://mlsanity.com/paper/2305.02637/) (2023)

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

- [Causality Guided Representation Learning for Cross-Style Hate Speech Detection](https://mlsanity.com/paper/2510.07707/) (2025)

## Abstract (arXiv)

Content moderation faces a challenging task as social media's ability to spread hate speech contrasts with its role in promoting global connectivity. With rapidly evolving slang and hate speech, the adaptability of conventional deep learning to the fluid landscape of online dialogue remains limited. In response, causality inspired disentanglement has shown promise by segregating platform specific peculiarities from universal hate indicators. However, its dependency on available ground truth target labels for discerning these nuances faces practical hurdles with the incessant evolution of platforms and the mutable nature of hate speech. Using confidence based reweighting and contrastive regularization, this study presents HATE WATCH, a novel framework of weakly supervised causal disentanglement that circumvents the need for explicit target labeling and effectively disentangles input features into invariant representations of hate. Empirical validation across platforms two with target labels and two without positions HATE WATCH as a novel method in cross platform hate speech detection with superior performance. HATE WATCH advances scalable content moderation techniques towards developing safer online communities.