Associate Professor Lexing Xie (1)

(1) Research School of Computer Science, Australian National University


How did a video go viral? Or will it go viral, and when? These are some of the most intriguing yet difficult questions in social media analysis. This talk will first provide a broad overview of recent research in understanding the predicting popularity, driven by larger amounts of online data and more understanding of human perception and psychology.

I will cover a few recent results from my group on understanding and predicting popularity, especially for YouTube videos. I will start by describing a unique longitudinal measurement study on video popularity history, and introduce popularity phases, a novel way to describe the evolution of popularity over time. I will then discuss a physics-inspired stochastic model that connects exogenous stimuli and endogenous responses to explain and forecast popularity. With such novel representation and new models, we can correlate video content type to popularity patterns, make better predictions, describe the endo-exo factors driving popularity, and forecast the effects of promotion campaigns.

This talk will cover join work with Dr Marian-Andrei Rizoiu, Dr Honglin Yu, Swapnil Mishra, Siqi Wu at the ANU, Prof Scott Sanner at U Toronto, Prof. Pascal van Hentenryck at U Michigan.