A Keyframe-Based Approach for Auditing Bias in YouTube Shorts Recommendations
By: Mert Can Cakmak, Nitin Agarwal
Potential Business Impact:
Shows how YouTube videos change what you see.
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.
Similar Papers
Relative Advantage Debiasing for Watch-Time Prediction in Short-Video Recommendation
Machine Learning (CS)
Fixes video suggestions to show what you'll like.
Multimodal Foundation Model-Driven User Interest Modeling and Behavior Analysis on Short Video Platforms
Information Retrieval
Shows you videos you'll actually like.
FOCUS: Efficient Keyframe Selection for Long Video Understanding
CV and Pattern Recognition
Lets AI understand long videos using fewer frames.