Bluesky feed engagement — image-count analysis
Context: this is a baseline for the pre-swipe-carousel era. Most posts in this sample were viewed under Bluesky's legacy multi-photo grid layout. A follow-up would test whether the swipe-carousel change alters the 4-image penalty.
*** p < 0.001
** p < 0.01
* p < 0.05
ns not significant
·
Cliff's d: <0.1 negligible · 0.1–0.3 small · 0.3–0.5 medium · >0.5 large
TL;DR
- 1 vs 2+ photos — essentially tied. Mann-Whitney p=0.13 ns, Cliff's d=−0.02 (negligible).
- 4-image posts underperform everything else (real & meaningful). Mean 28.6 likes vs 51.7 for 1-img; Cliff's d=+0.20 (small), p=4e-13 ***.
- 4-img drop is not a time-of-day artifact. Stouffer z=7.4 after stratifying by hour.
- The 4-img penalty is moderated by account size (small & large accounts feel it; medium doesn't).
- With typical-length captions (50–150 chars), the 4-img penalty vanishes (p=0.75 ns).
- Follower count is the dominant predictor (Spearman r=+0.47; regression IRR=2.0 per log unit).
Sample
Top-line: 1 photo vs 2+ photos
Means across engagement metrics
Per-image count (1 vs 2 vs 3 vs 4)
Mean likes (95% bootstrap CI)
Pairwise Mann-Whitney (Holm-corrected) on likes
Dedicated comparisons
Correlation r values (likes ~ predictor)
Time of day
Mean likes by hour of day (UTC)
Author "size" — two definitions, side by side
The left chart tiers authors by actual follower count (at analysis time). The right chart tiers authors by median likes per post — a proxy for effective reach. Interesting divergence: under the follower definition, medium-size accounts show no 4-img penalty; under median-engagement, the pattern is different.
Tier-by-tier 1-vs-4 likes
Text features
The key moderator: with captions of 50–150 chars (typical length), 1-img and 4-img posts perform identically (p=0.75 ns). The 4-img penalty is concentrated in posts with very short captions.
Caption length by image count
Alt-text use by image count
1-vs-4 stratified by caption length
Additional analyses
Image orientation (all image posts)
Inequality: Gini by image count
Composition — per 100 likes
Multivariate regression
Negative binomial GLM: likes ~ image_count dummies + log(1+followers) + has_alt + caption_length + hour (sin/cos). This is the single most important result — it controls for everything at once.
Incident Rate Ratios (IRR) with 95% CI