Community-Aware Assessment of Social Textual Engagement and Resonance: A Human-Centric Perspective on User-Generated Content Evaluation
2026-06-01 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors argue that judging video quality should go beyond just how good the video looks and instead consider how well it connects with viewers as a community. They introduce a new way to assess videos called CASTER, which looks at social engagement and emotional impact, not just visuals. To do this, they created MEDEA, an AI that imagines how different types of viewers would respond emotionally and cognitively before scoring the video. The authors trained MEDEA carefully to think like a real audience and made a new benchmark dataset called CASTER-Bench to test their method. Their experiments show MEDEA understands and predicts community reactions better than existing approaches.
Video Quality AssessmentUser-Generated ContentMultimodal AnalysisSocial EngagementCommunity ResonanceChain-of-ThoughtReinforcement LearningHuman-Centered AIBenchmark DatasetPerspective-Taking
Authors
Tianjiao Li, Kai Zhao, Xiang Li, Yang Liu, Huyang Sun
Abstract
Traditional Video Quality Assessment (VQA) focuses narrowly on aesthetic fidelity, overlooking the complex social dynamics that define quality in User-Generated Content (UGC). In this work, we propose a paradigm shift from signal-centric metrics to human-centric resonance assessment. We introduce CASTER (Community-Aware Assessment of Social Textual Engagement and Resonance), a new task that evaluates whether a UGC item achieves positive community resonance based on its multimodal attributes rather than visual quality alone. To address this, we present MEDEA (Multimodal Engagement-Driven Evaluation Architecture), which introduces a novel Social Chain-of-Thought (Social-CoT) mechanism. Unlike traditional logical CoT, Social-CoT performs multimodal perspective-taking, instantiating diverse viewer personas to simulate collective cognitive and emotional reactions (i.e., the "community mind") before deriving a quality judgment. MEDEA is trained via a two-stage approach involving supervised fine-tuning and process-supervised reinforcement learning with Social Alignment Reward to ensure reasoning paths are grounded in authentic human social cognition. To support this task, we release CASTER-Bench, a comprehensive human-annotated benchmark covering diverse UGC categories. Experiments demonstrate that MEDEA significantly outperforms state-of-the-art baselines on CASTER-Bench while providing interpretable and empathetic reasoning paths that align with real community feedback.