Capturing transitions between users' semantically meaningful places using mobile devices


Lovett, T. and O'Neill, E., 2012. Capturing transitions between users' semantically meaningful places using mobile devices. In: MobiSys 2012: The Tenth International Conference on Mobile Systems, Applications, and Services, 2012-06-24 - 2012-06-28, Low Wood Bay, Lake District. New York, USA: ACM, pp. 11-16.

Related documents:

PDF (Authors' accepted version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1771kB) | Preview


    Due to their ubiquity and ever-increasing technical capabilities, mobile devices are often used as data collection tools by researchers in multiple fields, notably HCI and Ubicomp. Although the data gathered by mobile devices can be generated from sources such as the device users, it is difficult for researchers to capture ground truth and verify data integrity beyond controlled laboratory studies. This lack of knowledge about data integrity may, in turn, affect the quality of higher-level inferences made using the data. In this paper, we report on the experience and results of a hybrid laboratory/field study in which we use mobile devices to infer the moment at which users transition between self-defined semantically meaningful personal places. The results show that filtered device motion does appear to reflect these moments of transition well, but the nature of the research question makes verification difficult in a field study.


    Item Type Conference or Workshop Items (UNSPECIFIED)
    CreatorsLovett, T.and O'Neill, E.
    DepartmentsFaculty of Science > Computer Science
    Publisher StatementO_Neill_MCSS_2012.pdf: © ACM, 2012. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in MCSS '12 Proceedings of the 1st ACM workshop on Mobile systems for computational social science, 2012,
    ID Code31174


    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...