Visual Analytics Methodology for Scalable and Privacy-Respectful Discovery of Place Semantics from Episodic Mobility Dat
People using mobile devices for making phone calls, accessing the internet, or posting georeferenced contents in social media create episodic digital traces of their presence in various places. Availability of personal traces over a long time period makes
- PDF / 371,882 Bytes
- 5 Pages / 439.37 x 666.14 pts Page_size
- 67 Downloads / 174 Views
Fraunhofer Institute IAIS, Sankt Augustin, Germany {natalia.andrienko,gennady.andrienko, georg.fuchs}@iais.fraunhofer.de 2 City University London, London, UK 3 San Diego State University, San Diego, USA [email protected] 4 Institute of Geoecology and Geoinformation, Adam Mickiewicz University, Poznan, Poland
Abstract. People using mobile devices for making phone calls, accessing the internet, or posting georeferenced contents in social media create episodic digital traces of their presence in various places. Availability of personal traces over a long time period makes it possible to detect repeatedly visited places and identify them as home, work, place of social activities, etc. based on temporal patterns of the person’s presence. Such analysis, however, can compromise personal privacy. We propose a visual analytics approach to semantic analysis of mobility data in which traces of a large number of people are processed simultaneously without accessing individual-level data. After extracting personal places and identifying their meanings in this privacy-respectful manner, the original georeferenced data are transformed to trajectories in an abstract semantic space. The semantically abstracted data can be further analyzed without the risk of re-identifying people based on the specific places they attend.
1
Introduction
The topic of this presentation, based on [1], is semantic modeling and semantic analysis of mobility data (trajectories of people). Currently, the main approach to attaching semantics to mobility data is comparing the locations of points from trajectories with locations of known places of interest (POI) [2]. This approach, however, cannot identify places having personal meanings, such as home and work. Identifying personal places is a challenging problem requiring scalable methods that can cope with numerous trajectories of numerous people while respecting their personal privacy [3, 4]. Our contribution consists of such an approach and a method for semantic abstraction of mobility data enabling further analyses without compromising personal privacy. © Springer International Publishing Switzerland 2015 A. Bifet et al. (Eds.): ECML PKDD 2015, Part III, LNAI 9286, pp. 254–258, 2015. DOI: 10.1007/978-3-319-23461-8_25
Visual Analytics Methodology for Scalable and Privacy-Respectful Discovery
255
A special focus of the paper is episodic mobility data [5, 6], where large temporal and spatial gaps can exist between consecutive records, but the proposed approach also works for data with fine temporal resolution. It adheres to the visual analytics paradigm [7], which combines computational analysis methods, such as machine learning techniques, with interactive visual tools supporting human reasoning.
2
Problem Statement and Methodology Overview
The input data are episodic human mobility traces, such as records about the use of mobile phones or other mobile devices at various locations. Each record includes a person’s (user’s) identifier, time stamp, and location specification, which may be geogra
Data Loading...
