Social Networks Applied

Traditionally, social-network models have been descriptive rather than predictive. They’re built at a very coarse level, typically with only a few global parameters, and aren’t useful for predicting the network’s behavior. In the past, this was due largely to lack of data; the networks available for study were small and few and contained minimal information about each node. Fortunately, the Internet’s rise has changed this dramatically. Massive quantities of data on large social networks are available from blogs, knowledge-sharing sites, collaborative-filtering systems, online gaming, social-networking sites, newsgroups, chat rooms, and so on. These networks typically number in the tens of thousands to millions of nodes. They often contain sufficient information to build models of individual nodes, which we can then assemble into models of the networks they’re part of. This gives us an unprecedented level of detail in social-network analysis, along with the potential for new understanding, useful predictions, and their productive use in decision making. My colleagues and I have begun to build social-network models at this scale using data from the Epinions knowledge-sharing site, the EachMovie collaborative-filtering system, and others.1,2 These models let us design viralmarketing plans that maximize positive word of mouth among customers. In our experiments, this has made it possible to achieve much higher profits than if we ignored interactions among customers and the corresponding network effects, as traditional marketing does.