GeoTopics - A method and system to explore urban activity

GeoTopics is a system to explore geographical patterns of urban activity. The system collects publicly shared check-ins generated by Foursquare users, that reveal who spends time where, when, and on what type of activity. Specifically, each venue in the data is associated with the following features: an exact location, a category (e.g., restaurant or museum), the set of users who have checked-in there, and the time (time of day and day of week) they checked-in. The method at the core of the system is a sparse probabilistic modeling technique to learn associations between different regions of a city and multi-feature descriptions of urban activity. As an example, one might discover that the south of a city is strongly associated with restaurants, bars, and night-clubs that are active in the evening, while the north of the city is associated with cafeterias and parks that are active in the morning of weekends.

Data and Resources
To access the resources you must log in
  • DemoURL

    The resource: 'Demo' is not accessible as guest user. You must login to access it!
  • Codepython

    The source code for the demo and the underlying technique.

    The resource: 'Code' is not accessible as guest user. You must login to access it!
Additional Info
Field Value
Accessibility Both
AccessibilityMode Download
Area Urban Computing
Availability On-Line
Basic rights Distribution
CreationDate 2015-10-12
Creator Michael Mathioudakis,
Field/Scope of use Any use
Owner Mathioudakis, Michael,
ProgrammingLanguage Python; Javascript
Semantic Coverage people; cities
Sublicense rights No
Territory of use World Wide
ThematicCluster Human Mobility Analytics
UsageMode Download
system:type Method
Management Info
Field Value
Author Mathioudakis Michael
Maintainer Michael Mathioudakis
Version 1
Last Updated 26 September 2019, 12:28 (CEST)
Created 26 September 2019, 12:28 (CEST)