Mining Smartphone Data to Classify Life-Facets of Social Relationships
Jun-Ki Min, Jason Wiese, Jason I. Hong, and John Zimmerman
Computer Supported Cooperative Work (CSCW)
February 2013
People engage with many overlapping social networks and enact diverse social roles across different facets of their lives. Unfortunately, many online social networking services reduce most people’s contacts to “friend.” A richer computational model of relationships would be useful for a number of applications such as managing privacy settings and organizing communications. In this paper, we take a step towards a richer computational model by using call and text message logs from mobile phones to classifying contacts according to life facet (family, work, and social). We extract various features such as communication intensity, regularity, medium, and temporal tendency, and classify the relationships using machine-learning techniques. Our experimental results on 40 users showed that we could classify life facets with up to 90.5% accuracy. The most relevant features include call duration, channel selection, and time of day for the communication.
