Abstract:The rise in popularity of social media platforms, has resulted in millions of new, content pieces being created every day. This surge in content creation underscores the need to pay attention to our design choices as they can greatly impact how long content remains relevant. In today's landscape where regularly recommending new content is crucial, particularly in the absence of detailed information, a variety of factors such as UI features, algorithms and system settings contribute to shaping the journey of content across the platform. While previous research has focused on how new content affects users' experiences, this study takes a different approach by analyzing these decisions considering the content itself. Through a series of carefully crafted experiments we explore how seemingly small decisions can influence the longevity of content, measured by metrics like Content Progression (CVP) and Content Survival (CSR). We also emphasize the importance of recognizing the stages that content goes through underscoring the need to tailor strategies for each stage as a one size fits all approach may not be effective. Additionally we argue for a departure from traditional experimental setups in the study of content lifecycles, to avoid potential misunderstandings while proposing advanced techniques, to achieve greater precision and accuracy in the evaluation process.
Abstract:Short video applications pose unique challenges for recommender systems due to the constant influx of new content and the absence of historical user interactions for quality assessment of uploaded content. This research characterizes the evolution of embeddings in short video recommendation systems, comparing batch and real-time updates to content embeddings. The analysis investigates embedding maturity, the learning peak during view accumulation, popularity bias, l2-norm distribution of learned embeddings, and their impact on user engagement metrics. The study unveils the contrast in the number of interactions needed to achieve mature embeddings in both learning modes, identifies the ideal learning point, and explores the distribution of l2-norm across various update methods. Utilizing a production system deployed on a large-scale short video app with over 180 million users, the findings offer insights into designing effective recommendation systems and enhancing user satisfaction and engagement in short video applications.