The accuracy of passive phone sensors in predicting daily mood

ABSTRACT

Daily phone usage data were collected passively from 271 Android phone users participating in a fully remote randomized controlled trial of depression treatment (BRIGHTEN). Participants completed daily Patient Health Questionnaire-2. A machine learning approach was used to predict daily mood for the entire sample and individual participants. Passive smartphone data with current features may not be suited for predicting daily mood at a population level because of the high degree of intra- and interindividual variation in phone usage patterns and daily mood ratings. Personalized models show encouraging early signs for predicting an individual's mood state changes, with GPS-derived mobility being the top most important feature in the present sample.

CITATION

Pratap, A., Atkins, D., Renn, B., Tanana, M. J., Mooney, S., Anguera, J., & Arean, P. (In Press) The accuracy of passive phone sensors in predicting daily mood. Depression and Anxiety. First published online: 21 August 2018.

Go to journal article

 

Blog Search