WalkNRide: contextualising feedback in physical activity trackers

Increasing levels of sedentarism and obesity, along with advances in sensor technologies have instigated a market for wearable activity trackers, electronic devices that sense users’ physical activity levels with the goals of self-monitoring and behaviour change. Nowadays, activity trackers are one of the most desirable technologies, making up for a market of over $230 million in 2013. However, despite the spike of users’ interest, activity trackers have been shown to lose their appeal over time, with a recent survey suggesting that one out of three users discard the tracker in the course of the first six months of use. The question we pose is: how can we design activity tracker so that users’ interests is sustained over the long term? Our design approach focuses on contextualising physical activity. We do this through sensing users’ locations and activities (such as being still, walking or commuting through a car, bus or other means) and thus providing innovative ways of presenting feedback on users. This thesis presents the design and evaluation of WalkNRide, a physical activity tracker for Google Android. Through a longitudinal field study of WalkNRide, we attempt to inquire into the factors that drive the adoption (or non-adoption) of the tool as well as the ways in which the use of the tool contributes towards habit formation.

Predicting and breaking sedentary behaviour at work

This thesis aimed at designing and developing a system that can a) infer individuals’ need for a break from sedentary behaviour in the workplace, and b) persuade them to take a break through the use of different techniques from persuasive psychology. We postulated three variables, namely, individuals’ posture, stress levels and involvement in their computer mediated activity. We developed and field-studied a system that could infer these using a web camera and a key presses and mouse clicks log. We found that the system could predict posture from viewing depth and stress from the movement detected. We then created a general formula that predicts individuals’ need for a break using only the posture and stress predictors. Once the first objective was set, we built and field-studied a system that used three ways to communicate a recommendation for a break to a user: implicit, just-in time and ambient feedback. The implicit feedback was operationalized through changes in the users’ computer wallpaper that provided subtle visual cues. The just-in time feedback employed prompting at the bottom right side of the user’s screen. In addition, we implemented an intuitive behind-screen interaction technique where people can snooze a notification using simple gestures. The ambient feedback mechanism employed an origami sculpture sitting on the user’s desk. This prototype was continuously reflecting the user’s posture and performed rhythmic movements when to recommend breaks. A field study demonstrated the overall success of the system, with 69% of the break recommendations received by users were accepted. The study further revealed the strengths and weaknesses of the three persuasive mechanisms.