# Toxicity in the Decentralized Web and the Potential for Model Sharing

arXiv: https://arxiv.org/abs/2204.12709 · HTML: https://mlsanity.com/paper/2204.12709/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2022.

## Built on by (most cited first, 6 of 6)

- [Safeguarding Decentralized Social Media: LLM Agents for Automating Community Rule Compliance](https://mlsanity.com/paper/2409.08963/) (2024)
- [Lady and the Tramp Nextdoor: Online Manifestations of Economic Inequalities in the Nextdoor Social Network](https://mlsanity.com/paper/2304.05232/) (2023)
- [Decentralised Moderation for Interoperable Social Networks: A Conversation-based Approach for Pleroma and the Fediverse](https://mlsanity.com/paper/2404.03048/) (2024)
- [Fedivertex: a Graph Dataset based on Decentralized Social Networks for Trustworthy Machine Learning](https://mlsanity.com/paper/2505.20882/) (2025)
- [Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure](https://mlsanity.com/paper/2604.25580/) (2026)
- [PIXELMOD: Improving Soft Moderation of Visual Misleading Information on Twitter](https://mlsanity.com/paper/2407.20987/) (2024)

## Abstract (arXiv)

The "Decentralised Web" (DW) is an evolving concept, which encompasses technologies aimed at providing greater transparency and openness on the web. The DW relies on independent servers (aka instances) that mesh together in a peer-to-peer fashion to deliver a range of services (e.g. micro-blogs, image sharing, video streaming). However, toxic content moderation in this decentralised context is challenging. This is because there is no central entity that can define toxicity, nor a large central pool of data that can be used to build universal classifiers. It is therefore unsurprising that there have been several high-profile cases of the DW being misused to coordinate and disseminate harmful material. Using a dataset of 9.9M posts from 117K users on Pleroma (a popular DW microblogging service), we quantify the presence of toxic content. We find that toxic content is prevalent and spreads rapidly between instances. We show that automating per-instance content moderation is challenging due to the lack of sufficient training data available and the effort required in labelling. We therefore propose and evaluate ModPair, a model sharing system that effectively detects toxic content, gaining an average per-instance macro-F1 score 0.89.