Is access frequency adequate for video popularity ranking in P2P streaming systems?
- 1 May 2012
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1233-1237
Abstract
Video popularity ranking is commonly used in various streaming systems. Existing popularity ranking systems usually rank videos from the perspective of access frequency and ignore other implicit feedback, due to the belief that popularity rankings with different implicit metrics are highly consistent. Based on a large collection of real-world system trace data, this paper systematically compares video popularity rankings with four different implicit metrics: access frequency, access user frequency, watching time, normalized watching time. We not only analyze the temporal dynamics of videos' popularities ranking with different metrics, but also examine the correlation between them. We have two main findings. 1) The popularities rankings with access frequency and watching time have strong correlation, but the other pairs have low consistency. 2) The temporal dynamics of daily rankings are similar, while the popularity rankings by access frequency and user number frequency are more stable than others. This paper also proposes a new top-N rank correlation coefficient and proves its efficiency. Our analysis results indicate that the implicit metric of popularity ranking needs to be carefully chosen according to specific applications.Keywords
This publication has 10 references indexed in Scilit:
- Describing and forecasting video access patterns2011
- Performance of recommender algorithms on top-n recommendation tasks2010
- Modeling user activities in a large IPTV system2009
- Modeling channel popularity dynamics in a large IPTV system2009
- Analyzing the Video Popularity Characteristics of Large-Scale User Generated Content SystemsIEEE/ACM Transactions on Networking, 2009
- Challenges, design and analysis of a large-scale p2p-vod system2008
- Temporal analysis of a very large topically categorized Web query logJournal of the American Society for Information Science and Technology, 2006
- Understanding user behavior in large-scale video-on-demand systems2006
- Clustered multimedia NOD: Popularity-based article prefetching and placement2003
- The Relation Between Measures of Correlation in the Universe of Sample PermutationsBiometrika, 1944