# Hate Raids on Twitch: Echoes of the Past, New Modalities, and Implications for Platform Governance

arXiv: https://arxiv.org/abs/2301.03946 · HTML: https://mlsanity.com/paper/2301.03946/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jan 2023.

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

- [Watch Your Language: Investigating Content Moderation with Large Language Models](https://mlsanity.com/paper/2309.14517/) (2023)
- [HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns](https://mlsanity.com/paper/2501.16750/) (2025)
- [Toxicity Detection is NOT all you Need: Measuring the Gaps to Supporting Volunteer Content Moderators](https://mlsanity.com/paper/2311.07879/) (2023)
- [Dimensions of Online Conflict: Towards Modeling Agonism](https://mlsanity.com/paper/2311.03584/) (2023)
- [ToxiTwitch: Toward Emote-Aware Hybrid Moderation for Live Streaming Platforms](https://mlsanity.com/paper/2601.15605/) (2026)
- [Silencing Empowerment, Allowing Bigotry: Auditing the Moderation of Hate Speech on Twitch](https://mlsanity.com/paper/2506.07667/) (2025)
- [The Triadic Loop: A Framework for Negotiating Alignment in AI Co-hosted Livestreaming](https://mlsanity.com/paper/2604.18850/) (2026)

## Abstract (arXiv)

In the summer of 2021, users on the livestreaming platform Twitch were targeted by a wave of "hate raids," a form of attack that overwhelms a streamer's chatroom with hateful messages, often through the use of bots and automation. Using a mixed-methods approach, we combine a quantitative measurement of attacks across the platform with interviews of streamers and third-party bot developers. We present evidence that confirms that some hate raids were highly-targeted, hate-driven attacks, but we also observe another mode of hate raid similar to networked harassment and specific forms of subcultural trolling. We show that the streamers who self-identify as LGBTQ+ and/or Black were disproportionately targeted and that hate raid messages were most commonly rooted in anti-Black racism and antisemitism. We also document how these attacks elicited rapid community responses in both bolstering reactive moderation and developing proactive mitigations for future attacks. We conclude by discussing how platforms can better prepare for attacks and protect at-risk communities while considering the division of labor between community moderators, tool-builders, and platforms.