Characterizing and modeling popularity of user-generated videos

Abstract

User-generated video content sites such as Youtube have become extremely popular. Understanding video online popularity is of great value for network and service providers, marketing industries, entertainment businesses and content creators. In this thesis, we develop novel frameworks to evaluate the impacts of different content-agnostic factors on Youtube videos popularity and use the resulting insights to study and model their popularity growth patterns. The first significant subject of our thesis is developing and applying a novel methodology that is able to accurately assess, both qualitatively and quantitatively, the impacts of various content-agnostic factors on video popularity. When controlling for video content, we observe a strong linear ``rich-get-richer'' behavior, with the total number of previous views as the most important factor except for very young videos. We analyze a number of phenomena that may contribute to rich-get-richer, including the first-mover advantage, and search bias towards popular videos. Our findings also confirm that inaccurate conclusions can be reached when not controlling for video content. The second central topic of our research is performing a characterization and modeling of the videos popularity dynamics using only the total view count for analysis. We develop a framework for studying the popularity dynamics of user-generated videos, present a characterization of the popularity dynamics, and propose a model that captures the key properties of these dynamics. 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. Another important aspect of our research is illustrating the biases that may be introduced in the analysis for some choices of the sampling technique used for collecting data.