Recent development of location technologies enables us to obtain the location history of users. This paper proposes a new method to infer users' long-term properties from their respective location histories. Counting the instances of sensor detection for every user, we can obtain a sensor-user matrix. After generating features from the matrix, a machine learning approach is taken to automatically classify users into different categories for each user property. Inspired by information retrieval research, the problem to infer user properties is reduced to a text categorization problem. We compare weightings of several features and also propose sensor weighting. Our algorithms are evaluated using experimental location data in an office environment.
|Number of pages||7|
|Journal||IJCAI International Joint Conference on Artificial Intelligence|
|Publication status||Published - 2007 Dec 1|
|Event||20th International Joint Conference on Artificial Intelligence, IJCAI 2007 - Hyderabad, India|
Duration: 2007 Jan 6 → 2007 Jan 12
ASJC Scopus subject areas
- Artificial Intelligence