Time-activity pattern observatory from mobile web logs

Air pollution has become a striking problem in recent years. When estimating the degree of human exposure to a particular air pollutant, time-activity pattern is one of the most important factors, which is able to quantify the time people spend in different micro-environments, such as indoor and outdoor. Traditional surveys use the method of questionnaires and telephone calls to explore the time-activity pattern. In this paper, we propose a novel method to analyse the time-activity pattern by utilising mobile web usage log. We test the method on two datasets covering about four million users. Experiments show that our method achieves an acceptable performance, and can truly measure the time-activity pattern of human beings.