Per Va Si V E Computing

A s smartphones proliferate through out society, so too does the opportunity to leverage these devices to study, understand, and positively affect human behavior. The growing opportunity to research and influence people’s daily lives has two primary catalysts. First, device manufacturers are quickly developing smartphones with rich capabilities in terms of computational power and sensor availability. Second, the developing culture around smartphones focuses on usage rather than the devices themselves, which many users consider indispensable. (For more information, see the “Smartphone Advances Present Opportunities” sidebar.) Rapid technological developments and the widespread adoption of smartphones raises the question of whether smartphones could provide an effective mechanism for tackling ongoing challenges related to the global population’s health and well-being. For example, in the US, 26 percent of the adult population is obese,1 and smoking kills nearly six million people every year.2 Similarly, about one in six Americans report a history of depression.3 In many of these cases, lifestyle changes—brought on by informing, teaching, and supporting those who seek to change— might lead to positive health outcomes. Behavior-change interventions (BCIs) are a well-studied means that behavioral scientists have developed to induce these changes. These techniques have recently been brought online and can now be delivered over the Internet. However, they have yet to be fully ported to and integrated with sensor-enhanced smartphones. Recent work has shown that we can make inferences about user contexts, physical activities,4,5 and mental states (including emotions6 and stress7) using data from smartphone sensors, which has great potential for BCIs. For example, weight-reduction interventions are tied to the participants’ physical activity, while interventions related to mood disorders are inherently related to monitoring participants’ mental states. Here, we examine open questions and challenges related to merging smartphone sensing and BCI applications. We highlight recent work from the mobile sensing domain and describe how it can support the design of smartphone BCIs. In particular, we present two applications for behavioral monitoring and change—EmotionSense and SensibleSense, respectively—and Equipped with cutting-edge sensing technology and high-end processors, smartphones can unobtrusively sense human behavior and deliver feedback and behavioral therapy. The authors discuss two applications for behavioral monitoring and change and present UBhave, the first holistic platform for large-scale digital behavior change intervention.