The Problem: Predicting Popularity in Social Media

– Predicting popularity is an important open problem in social media. – Most current methods operate under the assumption that past popularity implies future popularity (Figure 2 Left). However, this approach cannot account for sudden changes, or when popularity history is unknown (Figure 2 Right). – We propose a novel system to connect across two social networks, and provide an affirma-tive answer for the question: Can Twitter help predict YouTube popularity? – This work takes the first steps towards answering questions like “will an obscure video suddenly become very popular, and when”, or “which videos will be the most popular in 1, 2, or 3 months”? contributed articles AUGUST 2010 | VOL. 53 | NO. 8 | COMMUNICATIONS OF THE ACM 83 ties, YouTube videos keep attracting views throughout their lifetimes. The rate videos attract views may naturally differ among videos, with the less-pop-ular likely marking a slower pace over a longer time. These two notably different user-popularity patterns are a consequence of how users react to content on the two portals. On Digg, articles quickly be-come obsolete, since they often link to breaking news, fleeting Internet fads, or technology-related themes with a naturally limited time for user appeal. However, videos on YouTube are mostly found through search, since, with the sheer number of videos constantly be-ing uploaded, it is not possible to match Digg’s way of giving each promoted sto-ry general exposure on a front page. The quicker initial rise of video view counts can be explained through the videos ’ ex-posure in YouTube’s “recently added” section, but after leaving it, the only way to find them is through keyword search or when displayed as related videos next to another video being watched. The short fad-like popularity life cycle of Digg stories (a day or less) sug-gests that if overall user activity on Digg depends on time of day, a story’s popu-larity may grow more slowly when fewer visitors are on the site and increase more quickly at peak periods. For You-Tube, this effect is less relevant, since video views are spread over more time