WellBeat | A Framework for Tracking Daily Well-being Using Smartwatches


Are people's heart rate changes predictive of their well-being and, if so, at which temporal granularity?

Human physiology is a window to our physical, mental, and emotional states; our well-being. Today, a new wave of objective data derived from consumer-grade body sensors-like those equipped by smartwatches-paves the way towards a new approach in how well-being is being measured, continuously and unobtrusively. Nokia Bell Labs researchers developed WellBeat, a framework for collecting and analyzing physiological data using smartwatches in-the-wild. Its robustness in data collection and quality allowed the researchers to study people's heart rate changes and their well-being away from controlled laboratory settings.

Using an Experience Sampling Method, they conducted a three-week longitudinal study to investigate the extent to which people's heart changes are associated with their well-being and, particularly, with happiness, awakedness, and relaxedness levels. Using WellBeat's 6-step data processing pipeline, they extracted heart rate and heart rate variablity parameters, and ensured reliable estimates. With these parameters at hand, they investigated the extent to which heart rate changes are associated with people's well-being at two aggregation levels: momentary and daily. They found that changes in people's heart rate and heart rate variability are predictive not of momentary well-being (a scientific idea that continues to live on in the absence of in-the-wild evidence, aka, zombie theory) but of daily well-being.

WellBeat's watch application and data processing pipeline can serve as the basis to unlock a wide range of applications, starting from the workplace. For example, employees could wear watches and get an immediate feedback of the workplace's atmosphere via an interactive installation where emotional states are aggregated and visualized in a playful way through HeartBees' visualization. Such visualizations are made possible due to the underlying technology provided by WellBeat.

HeartBees visualization demo

HeartBees-vis
HeartBees. A metaphorical visualization that uses the movements of a flock of birds in a plane to represent eight basic emotions: fear, anger, anticipation, trust, surprise, disgust, joy, and sadness. Physiological data obtained from watches and analyzed through WellBeat are mapped into a multi-dimensional emotion model, which in turn HeartBees translates into a metaphorical visualization of a flock of birds.

Publications

  • WellBeat: A Framework for Tracking Daily Well-being Using Smartwatches. IEEE Internet Computing 2020 PDF
  • HeartBees: Visualizing Crowd Affects. IEEE VISAP 2020 PDF
  • Having a Heart Time? A Wearable-based Biofeedback System. MobileHCI Demo 2020 PDF