Sensing the 'Health State' of our Society

Abstract

Mobile phones are a pervasive platform for opportunistic sensing of behaviors and opinions. We show that location and communication sensors can be used to model individual symptoms, long-term health outcomes, and diff usion of opinions in society. For individuals, phone-based features can be used to predict changes in health, such as common colds, influenza, and stress, and automatically identify symptomatic days. For longer-term health outcomes such as obesity, we fi nd that weight changes of participants are correlated with exposure to peers who gained weight in the same period, which is in direct contrast to currently accepted theories of social contagion. Finally, as a proxy for understanding health education we examine change in political opinions during the 2008 US presidential election campaign. We discover dynamic patterns of homophily and use topic models (Latent Dirchlet Allocation) to understand the link between specfii c behaviors and changes in political opinions.