During my PhD research, I focused on utilising physiological data from wearable devices to detect stress and emotions. I was especially interested how we can leverage data of consumer devices in everyday life situations.

A first pilot study of mine focused on using Apple Watch sensing data and mood experience samples of participants. The pilot ran for 7 days and participants rated their mood several times throughout the day. For this study, I provided an Apple Watch App called ‘EmoRate’ which promts the user several times a day to rate their current emotional state in terms of positivity and arousal with a simple and quick input. In the background, the app collects sensing data, such as heart rate, wrist movement, and location (optional). I presented the concept of this app at the UbiComp’16 Mental Health and Well-Being workshop.

In summer 2017, I conducted a study comparing different consumer wearable sensing technologies regarding their suitability to detect stress in a controlled lab setting. For this study, I developed a framework to easily collect sensing data from the Apple Watch the AWSense framework was presented as a demo at MobiSys’17. The results of the study will be presented at CHI’18.

During the last months of my PhD studies, I conducted a study with Kleomenis Katevas on using mobile and wearable sensing in a social mingling scenario. We collected rich mobile phone data (accelerometer/gyroscope, bluetooth proximity) and wearable data (heart rate, EDA, skin temperature, wrist movements) of participants while they were socially interacting. I am especially interested in synchronisation of the physiological data and emotions during social interaction.