Understanding Virality: A Rubric based Vision-Language Model Framework for Short-Form Edutainment Evaluation
This work addresses the need for human-aligned, interpretable evaluation in short-form edutainment videos, though it is incremental as it builds on existing multimodal methods.
The paper tackled the problem of evaluating short-form video content by proposing a framework that uses Vision-Language Models to predict engagement, achieving strong correlations with actual engagement metrics.
Evaluating short-form video content requires moving beyond surface-level quality metrics toward human-aligned, multimodal reasoning. While existing frameworks like VideoScore-2 assess visual and semantic fidelity, they do not capture how specific audiovisual attributes drive real audience engagement. In this work, we propose a data-driven evaluation framework that uses Vision-Language Models (VLMs) to extract unsupervised audiovisual features, clusters them into interpretable factors, and trains a regression-based evaluator to predict engagement on short-form edutainment videos. Our curated YouTube Shorts dataset enables systematic analysis of how VLM-derived features relate to human engagement behavior. Experiments show strong correlations between predicted and actual engagement, demonstrating that our lightweight, feature-based evaluator provides interpretable and scalable assessments compared to traditional metrics (e.g., SSIM, FID). By grounding evaluation in both multimodal feature importance and human-centered engagement signals, our approach advances toward robust and explainable video understanding.