Audience feedback is crucial for refining video content, yet it typically comes after publication, limiting creators' ability to make timely adjustments. To bridge this gap, we introduce SimTube, a generative AI system designed to simulate audience feedback in the form of video comments before a video's release. SimTube features a computational pipeline that integrates multimodal data from the video-such as visuals, audio, and metadata-with user personas derived from a broad and diverse corpus of audience demographics, generating varied and contextually relevant feedback. Furthermore, the system's UI allows creators to explore and customize the simulated comments. Through a comprehensive evaluation-comprising quantitative analysis, crowd-sourced assessments, and qualitative user studies-we show that SimTube's generated comments are not only relevant, believable, and diverse but often more detailed and informative than actual audience comments, highlighting its potential to help creators refine their content before release.

翻译：观众反馈对于优化视频内容至关重要，但其通常在视频发布后才产生，限制了创作者及时调整内容的能力。为弥合这一差距，我们提出了SimTube，一个生成式人工智能系统，旨在视频发布前以评论形式模拟观众反馈。SimTube采用一个计算流程，该流程整合了来自视频的多模态数据——如视觉、音频和元数据——以及从广泛多样的受众人口统计学语料库中提取的用户画像，从而生成多样化且与上下文相关的反馈。此外，系统的用户界面允许创作者探索并定制模拟评论。通过包含定量分析、众包评估和定性用户研究的综合评估，我们证明SimTube生成的评论不仅具有相关性、可信度和多样性，而且通常比真实观众评论更为详细和富有信息量，这凸显了其在帮助创作者于发布前优化内容方面的潜力。