Towards personal stress informatics: comparing minimally invasive techniques for measuring daily stress in the wild

Identifying episodes of significant stress is a challenging problem with implications for personal health and interface adaptation. We present the results of a study comparing multiple modalities of minimally intrusive stress sensing in real-world environments, collected from seven participants as they carried out their everyday activities over a ten-day period. We compare the data streams produced by sensors and self-report measures, in addition to asking the participants, themselves, to reflect on the accuracy and completeness of the data that had been collected. Finally, we describe the range of participant experiences—both positive and negative—as they reported their everyday stress levels. As a result of this study, we demonstrate that voice-based stress sensing tracks with electrodermal activity and self-reported stress measures in real-world environments and we identify limitations of various sensing approaches.