This paper presents new methods for inferring colocation and conversation networks from fine-grained behavioral data collected automatically using wearable sensors. We discuss how we can derive meaningful information about social interaction from audio data, while protecting the privacy of human subjects. We apply these methods in a study of face-to-face interactions among 24 students in a graduate school cohort during an academic year.

Wyatt, Danny, Choudhury, Tanzeem, Bilmes, Jeff, and James A. Kitts. “Inferring Colocation and Conversational Networks Using Privacy-Sensitive Audio” ACM Transactions on Intelligent Systems and Technology, 2(1), 2011.