Discovering Daily Routines from Google Latitude with Topic Models

Discovering users’ whereabouts patterns is importantfor many emerging ubiquitous computing applications.Life-log systems, advertisement and smart environments areonly some of the applications that can be supported byinformation regarding user patterns and routine behaviors.Latent Dirichlet Allocation (LDA) is a powerful mechanismto extract recurrent behaviors and high-level patterns (calledtopics) from mobility data in an unsupervised manner. In thispaper we test the effectiveness of LDA in identifying users’routine behaviors from mobility data collected with GoogleLatitude. Results show that the proposed technique providesgood results in discovering patterns and routine behaviors.