用新数据集和两个指标，仅凭视频内容预测短视频受欢迎程度。
Delving Deep into Engagement Prediction of Short Videos
- 构建9万条Snapchat真实短视频数据集，提出NAWP与ECR新指标。
- 发现视频质量评分与实际受欢迎程度无关，需依赖内容特征预测。
- 融合视觉、音乐、文字多模态信息，实现纯内容驱动的推荐预测。
理解并建模社交媒体平台中用户生成内容（UGC）短视频的流行度，对内容创作者和推荐系统具有重要意义。本研究深入探讨了对发布后互动较少的新视频进行参与度预测的挑战。令人意外的是，以往视频质量评估数据集中的平均意见分与视频参与度关联性不强。为此，我们构建了一个包含90,000条真实UGC短视频的大规模数据集，来自Snapchat。不同于传统的播放量、平均观看时长或点赞率，我们提出两个新指标：归一化平均观看百分比（NAWP）和参与延续率（ECR），用于描述短视频的参与水平。研究还考察了多种多模态特征，包括视觉内容、背景音乐和文本信息，以提升参与度预测能力。基于所提数据集和关键指标，我们的方法证明可仅通过视频内容准确预测其参与度。
原文摘要 · Abstract (English)
Understanding and modeling the popularity of User Generated Content (UGC) short videos on social media platforms presents a critical challenge with broad implications for content creators and recommendation systems. This study delves deep into the intricacies of predicting engagement for newly published videos with limited user interactions. Surprisingly, our findings reveal that Mean Opinion Scores from previous video quality assessment datasets do not strongly correlate with video engagement levels. To address this, we introduce a substantial dataset comprising 90,000 real-world UGC short videos from Snapchat. Rather than relying on view count, average watch time, or rate of likes, we propose two metrics: normalized average watch percentage (NAWP) and engagement continuation rate (ECR) to describe the engagement levels of short videos. Comprehensive multi-modal features, including visual content, background music, and text data, are investigated to enhance engagement prediction. With the proposed dataset and two key metrics, our method demonstrates its ability to predict engagements of short videos purely from video content.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。