Journal cover Journal topic
AGILE: GIScience Series Open-access proceedings of the Association of Geographic Information Laboratories in Europe
Journal topic
Articles | Volume 2
AGILE GIScience Ser., 2, 1, 2021
AGILE GIScience Ser., 2, 1, 2021

  04 Jun 2021

04 Jun 2021

Information-optimal Abstaining for Reliable Classification of Building Functions

Gabriel Dax and Martin Werner Gabriel Dax and Martin Werner
  • Technical University of Munich, Department of Aerospace and Geodesy, Big Geospatial Data Management, Munich, Germany

Keywords: Probabilistic Classification, Social Media Text Mining, Land Use, Urban Analysis, Building Functions

Abstract. In the past decade, major breakthroughs in sensor technology and algorithms have enabled the functional analysis of urban regions based on Earth observation data. It has, for example, become possible to assign functions to areas in cities on a regional scale. With this paper, we develop a novel method for extracting building functions from social media text alone. Therefore, a technique of abstaining is applied in order to overcome the fact that most tweets will not contain information related to a building function albeit they have been sent from a specific building as well as the problem that classification schemes for building functions are overlapping.

Publications Copernicus