Social networks have become a fixture of modern life, thanks to social networking sites such as Facebook and Twitter. Social networks themselves are not new, however. The study of such networks dates back to the early twentieth century, particularly in the fields of sociology and anthropology. It is their prevalence in mainstream applications that has moved these types of studies to the purview of data science.

It turns out that social networks are extremely interesting as models for human behavior. Human civilization stems from tribal societies and as a result, Dunbar's number-a hypothesis that at any given time we can only have 150 people in our extended social network-has famously been proven through the analysis of the most active networks. Latent social networks exist everywhere, not just in popular web 2.0 applications. We manage our lives through connections to various networks, and, because of that, we generate a lot of related, rich data that can be used to make predictions...