Identifying and understanding urban sport areas using Nokia Sports Tracker

Abstract

Current advancements in pervasive technologies allow users to create and share an increasing amount of whereabouts data. Thus, some rich datasets on human mobility are becoming available on the web. In this paper we extracted approximately 790,000 mobility traces from a web-based repository of GPS tracks—the Nokia Sports Tracker Service. Using data mining mechanisms, we show that this data can be analyzed to uncover daily routines and interesting schemes in the use of public spaces. We first show that our approach supports large-scale analysis of people’s whereabouts by comparing behavioral patterns across cities. Then, using Kernel Density Estimation, we present a mechanism to identify popular sport areas in individual cities. This kind of analysis allows us to highlight human-centered geographies that can support a wide range of applications ranging from location-based services to urban planning.