Metraipolis › archive › dc_2dff14095df9
Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscape of Harms — arXiv:2609.11373
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.11373
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T05:27:02.126Z
- SHA-256 of the archived text
e42f0572ff3355fdb41ee6d8e24c08bc7b369b685dd9c93640408c4022999745- Stable URL of this page
https://metraipolis.com/documento/dc_2dff14095df9
How to cite
Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscape of Harms — arXiv:2609.11373 — arXiv (en), https://arxiv.org/abs/2609.11373 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2dff14095df9 (Metraipolis archive dc_2dff14095df9, sha256 e42f0572ff3355fdb41ee6d8e24c08bc7b369b685dd9c93640408c4022999745)
BibTeX
@misc{dc2dff14095df9,
title = {Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscape of Harms — arXiv:2609.11373},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.11373},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2dff14095df9; sha256 e42f0572ff3355fdb41ee6d8e24c08bc7b369b685dd9c93640408c4022999745},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11373. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Empirical research on content moderation is fundamentally constrained by the opaque deployment of moderation systems on major social media platforms. To this end, the recent emergence of decentralized platforms with transparent, public moderation logs presents an unprecedented opportunity for independent audits. In this work, we leverage this architectural transparency to conduct the first large-scale audit of the default moderation system on Bluesky, the Bluesky Moderation Service (BMS). Analyzing its 10.6M moderation labels from 2025, we investigate three foundational aspects: (i) its mechanism (the degree of automation versus human oversight), (ii) its efficacy (accuracy in detecting harms), and (iii) its purpose (the landscape of harms it identifies). Our findings reveal a human-AI collaborative system where labels for sexual and graphic content are applied automatically in seconds, while nuanced and high stakes labels require more human oversight, taking hours or days. Through a manual annotation study, we find the BMS operates with high precision (0.837), but struggles with low recall (0.222), with our annotators identifying 4.5$\times$ more harmful content than the moderation system in a random sample. Finally, unsupervised clustering of the most frequently applied labeled posts uncovers detected harms ranging from hostility in discourse toward protected groups to the spread of sexually explicit and other graphic content. Our work offers a look into the operational realities of a deployed moderation system, providing a concrete data-driven foundation for designing more effective and transparent moderation systems. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI). Categorie arXiv: Computers and Society (cs.CY) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.11373 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T05:17:52.155Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).