Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.02543 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916930231730176 |
|---|---|
| author | Cakmak, Mert Can Agarwal, Nitin |
| author_facet | Cakmak, Mert Can Agarwal, Nitin |
| contents | YouTube Shorts and other short-form video platforms now influence how billions engage with content, yet their recommendation systems remain largely opaque. Small shifts in promoted content can significantly impact user exposure, especially for politically sensitive topics. In this work, we propose a keyframe-based method to audit bias and drift in short-form video recommendations. Rather than analyzing full videos or relying on metadata, we extract perceptually salient keyframes, generate captions, and embed both into a shared content space. Using visual mapping across recommendation chains, we observe consistent shifts and clustering patterns that indicate topic drift and potential filtering. Comparing politically sensitive topics with general YouTube categories, we find notable differences in recommendation behavior. Our findings show that keyframes provide an efficient and interpretable lens for understanding bias in short-form video algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02543 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Keyframe-Based Approach for Auditing Bias in YouTube Shorts Recommendations Cakmak, Mert Can Agarwal, Nitin Social and Information Networks YouTube Shorts and other short-form video platforms now influence how billions engage with content, yet their recommendation systems remain largely opaque. Small shifts in promoted content can significantly impact user exposure, especially for politically sensitive topics. In this work, we propose a keyframe-based method to audit bias and drift in short-form video recommendations. Rather than analyzing full videos or relying on metadata, we extract perceptually salient keyframes, generate captions, and embed both into a shared content space. Using visual mapping across recommendation chains, we observe consistent shifts and clustering patterns that indicate topic drift and potential filtering. Comparing politically sensitive topics with general YouTube categories, we find notable differences in recommendation behavior. Our findings show that keyframes provide an efficient and interpretable lens for understanding bias in short-form video algorithms. |
| title | A Keyframe-Based Approach for Auditing Bias in YouTube Shorts Recommendations |
| topic | Social and Information Networks |
| url | https://arxiv.org/abs/2509.02543 |