Discovering daily routines from Google Latitude with topic models
Authors:
- 1 March 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 432-437
Abstract
Discovering users' whereabouts patterns is important for many emerging ubiquitous computing applications. Life-log systems, advertisement and smart environments are only some of the applications that can be supported by information regarding user patterns and routine behaviors. Latent Dirichlet Allocation (LDA) is a powerful mechanism to extract recurrent behaviors and high-level patterns (called topics) from mobility data in an unsupervised manner. In this paper we test the effectiveness of LDA in identifying users' routine behaviors from mobility data collected with Google Latitude. Results show that the proposed technique provides good results in discovering patterns and routine behaviors.Keywords
This publication has 12 references indexed in Scilit:
- Discovering routines from large-scale human locations using probabilistic topic modelsACM Transactions on Intelligent Systems and Technology, 2011
- The Power of Mobile Computing in a Social EraIEEE Internet Computing, 2010
- A survey of context modelling and reasoning techniquesPervasive and Mobile Computing, 2010
- Temporal task footprinting2010
- An Alignment Approach for Context Prediction Tasks in UbiComp EnvironmentsIEEE Pervasive Computing, 2010
- Understanding Recording Technologies in Everyday LifeIEEE Pervasive Computing, 2009
- Eigenbehaviors: identifying structure in routineBehavioral Ecology and Sociobiology, 2009
- Digital Footprinting: Uncovering Tourists with User-Generated ContentIEEE Pervasive Computing, 2008
- Supporting location-aware services for mobile users with the whereabouts diary2008
- MyLifeBitsCommunications of the ACM, 2006