Abstract

Providers such as YouTube o er easy access to multimedia content to millions, generating high bandwidth and storage demand on the Content Delivery Networks they rely upon. More and more, the di usion of this content happens on online social networks such as Facebook and Twitter, where social cascades can be observed when users increasingly re- post links they have received from others. In this paper we describe how geographic information ex- tracted from social cascades can be exploited to improve caching of multimedia les in a Content Delivery Network. We take advantage of the fact that social cascades can prop- agate in a geographically limited area to discern whether an item is spreading locally or globally. This informs cache re- placement policies, which utilize this information to ensure that content relevant to a cascade is kept close to the users who may be interested in it. We validate our approach by using a novel dataset which combines social interaction data with geographic information: we track social cascades of YouTube links over Twitter and build a proof-of-concept geographic model of a realis- tic distributed Content Delivery Network. Our performance evaluation shows that we are able to improve cache hits with respect to cache policies without geographic and social in- formation.