I tube, you tube, everybody tubes: analyzing the world's largest user generated content video system
Proceedings of the 7th ACM SIGCOMM conference on Internet measurement
Computer Networks: The International Journal of Computer and Telecommunications Networking
The impact of YouTube recommendation system on video views
IMC '10 Proceedings of the 10th ACM SIGCOMM conference on Internet measurement
Watching user generated videos with prefetching
MMSys '11 Proceedings of the second annual ACM conference on Multimedia systems
Boosting video popularity through recommendation systems
Databases and Social Networks
Hi-index | 0.00 |
Following advice from the YouTube recommendation system is one of the ways users browse through the videos offered by YouTube. The system presents related videos based on several factors depending on the current video requested. This related videos list can be used by caching infrastructure to reduce network bandwidth consumption. In this paper, we analyze the differences between user-specific recommendation lists. We perform this analysis on 100s of user nodes from all around the world divided into 4 geographical regions using PlanetLab. Based on our analysis, we find that the related videos differ less in the top half (1-10) of the related video list offered by YouTube compared to the bottom half (11-20). Based on our analysis, we suggest that, caching or prefetching of the Top 10 of the related videos is advantageous over a period of time than caching the whole list offered by YouTube.