On Using Existing Time-Use Study Data for Ubiquitous Computing
K. Partridge and P. Golle.
Governments and commercial institutions have conducted detailed time-use
studies for several decades. In these studies, participants give a
detailed record of their activities, locations, and other data over a day,
week, or longer period. These studies are particularly valuable for the
ubicomp community because of the large number of participants (often the
tens of thousands), and because of their public availability. In this
paper, we show how to use the data from these studies to provide validated
and cheap (although noisy) classifiers, baseline metrics, and other
benefits for activity inference applications.