Mobile Sensing to Model the Evolution of Political Opinions

Exposure and adoption of opinions in social networks are important questions in education, business, and government. We describe a novel application of ubiquitous computing based on using mobile phone sensors to measure and model the face-to-face interactions and subsequent opinion changes of undergraduates during the US presidential election campaign. We find that self-reported political discussants have characteristic interaction patterns and can be predicted from sensor data. Mobile features can be used to estimate unique individual exposure to different opinions, and help discover surprising patterns of dynamic homophily related to external political events, such as election debates and election day (4th Nov 2008). To our knowledge, this is the first time such dynamic homophily effects have been measured. Using sensor features and estimated exposure and past opinions, it is possible to predict future opinions for individuals (R ̃0.8, p ̃0.001), and measured exposure increases explained variance by up to 30% over that of survey responses of past opinions alone.