This paper develops a framework for studying the popularity dynamics of user-generated videos, presents a characterization of the popularity dynamics, and proposes a model that captures the key properties of these dynamics. We illustrate the biases that may be introduced in the analysis for some choices of the sampling technique used for collecting data; however, sampling from recently-uploaded videos provides a dataset that is seemingly unbiased. Using a dataset that tracks the views to a sample of recently-uploaded YouTube videos over the first eight months of their lifetime, we study the popularity dynamics. We find that the relative popularities of the videos within our dataset are highly non-stationary, owing primarily to large differences in the required time since upload until peak popularity is finally achieved, and secondly to popularity oscillation. We propose a model that can accurately capture the popularity dynamics of collections of recently-uploaded videos as they age, including key measures such as hot set churn statistics, and the evolution of the viewing rate and total views distributions over time.

Abstract. With BitTorrent-like protocols a client may download a file from a large and changing set of peers, using connections of heterogeneous and timevarying bandwidths. This flexibility is achieved by breaking the file into many small pieces, each of which may be downloaded from different peers.This paper considers an approach to peer-assisted on-demand delivery of stored media that is based on the relatively simple and flexible BitTorrent-like approach, but which is able to achieve a form of "streaming" delivery, in the sense that playback can begin well before the entire media file is received. Achieving this goal requires: (1) a piece selection strategy that effectively mediates the conflict between the goals of high piece diversity, and the in-order requirements of media file playback, and (2) an on-line rule for deciding when playback can safely commence. We present and evaluate using simulation candidate protocols including both of these components.

No abstract

No abstract

No abstract