Whose Posts Get Ranked: Identical-Text Exposure Gaps in Bluesky Custom Feeds

2026-08-13

AI Summary

This study addresses exposure inequality in Bluesky’s custom recommendation algorithms by employing large-scale snapshot collection and fixed-effects regression to quantify, for the first time, impression disparities for identical content across independent recommenders. Results indicate that 33% of matched posts exhibit significant exposure gaps, with author historical interactions rather than content quality driving ranking outcomes. New authors receive an exposure weight penalty of 0.061 and achieve only a 26% win rate against established accounts. These findings demonstrate that diversified feeds fail to ensure equitable content visibility, revealing how accumulated historical advantages impose structural disadvantages on emerging creators. This work provides empirical evidence of algorithmic bias inherent in decentralized social platforms, highlighting critical challenges in achieving meritocratic content distribution within federated recommendation ecosystems.

Abstract

Bluesky lets users deploy custom feeds, independently operated recommendation algorithms that the platform serves alongside thousands of others. This paper investigates how evenly these feeds treat posts with the same text. To measure this, we take repeated snapshots of the Top-50 lists that 1,366 public feeds return, and we group posts with identical text, from different authors, that were created before the same list response and closely matched in age. Exposure diverges widely inside these matched sets, which span 250 feeds: in 33% of sets, one copy appears on the list while another does not. Fixed-effects regressions show that this divergence is associated with the author's history on the specific feed. Authors new to a feed receive less exposure for the same text (-0.061 in reciprocal-rank weight), while authors whose posts the feed has returned before receive more. A new author with more followers than the competing author still loses 74\% of head-to-head comparisons. Media and post-type features show no detectable association after multiple-comparison correction. These results are early evidence that access to many independent feeds is not enough to give identical texts equal exposure.

Problem

• Bluesky
• custom feeds
• exposure gap
• identical-text
• recommendation algorithms

Innovation

• Custom Feeds
• Exposure Gap
• Algorithmic Fairness
• Fixed-effects Regression
• Bluesky