Social interactions provide support for individuals and heavily influence the decisions they make. Understanding how information is extracted from social interactions and how that information influences our decisions could have a tremendous public health benefit. In this talk, I will describe experiments designed to elucidate how the brain constructs representations of complex social interactions and the network modeling and machine learning methods developed to study those processes. First, I will focus on the hierarchical construction of social information and tests of those mechanisms using support vector machines and hitting-time network measures. This model of social information processing has implications for the study of autism and for human computer interaction. Second, I will report on results from a multiplayer game that provides an experimental setting for the assessment of social influences on risky decision making. Risky choices made in the game correlate with reported drug and alcohol abuse. For each individual, the extent of influence by the play of others correlates with the likelihood of shoplifting. Neuroimaging data collected during game play provides early support for multiple mechanisms underlying social effects on risk taking. Finally, I will describe ongoing work to extend our research to the classroom with the target of improving student learning and engagement. This research provides a better understanding of how the brain represents social information and new methods for the study of information processing in the brain with implications for autism, interaction with autonomous agents, and the cultivation of healthy risk.