Anthony Hombiat - OF4OSM - un méta-modèle pour structurer la folksonomie OpenStreetMap en une nouvelle ontologie

09:30
Friday
24
Feb
2017
  • Thesis defence
Place: 
Organized by: 
Anthony Hombiat
Speaker: 
Anthony Hombiat
Teams: 

 

Composition du jury :

  • Mme Anne Ruas, ingénieur des Ponts, des Eaux et des Forêts (IPEF) à l'IFSTTAR, rapporteur
  • M. Christophe Cruz, maître de conférences HDR à l'Université de Bourgogne Franche-Comté (UBFC) au laboratoire Le2i, rapporteur
  • Mme Nathalie Aussenac-Gilles, directrice de recherche au CNRS à l'IRIT, examinatrice
  • M. Jérôme Euzenat, directeur de recherche HDR à l'INRIA, examinateur
  • Mme Marlène Villanova-Oliver, Maître de Conférences à l'Université Grenoble Alpes (UGA), co-encadrante de thèse
  • M. Jérôme Gensel, professeur à l'Université Grenoble Alpes (UGA), directeur de thèse
  • M. Guillaume Allègre, membre de l'association OpenStreetMap France, invité

Post-2000s web technologies have enabled users to engage in the information production process: Web 2.0 surfers are the new data sensors. Regarding Geographic Information (GI), large crowdsourced datasets emerge from the Volunteered Geographic Information (VGI) phenomenon through platforms such as OpenStreetMap. The latter involves more than three millions contributors who aim at mapping the world into an open geospatial database.

This deluge of VGI consists of spatial features that are described with tags. Content categorization with tags is typical of crowdsourcing platforms. However, this approach is also a major impediment to interoperability with other systems that could benefit from this huge amount of bottom-up data. Indeed, folksonomies are much less expressive data models than ontologies.

In this thesis, we address the issue of loose OSM metadata by proposing a metamodel for semantically lifting the OSM folksonomy while preserving the flexibility of the tagging activity. This meta-model supports the identification of different types of OSM tags and their semantification into an OSM knowledge base in the form of an ontology: OF4OSM. Comparatively to existing approaches, this ontology features a higher coverage of the OSM tags, an enhanced formal expressivity, a wider interconnection to other knowledge bases and a full compliance to the participatory philosophy of the OpenStreetMap project.

This work paves the way to the building of a knowledge base of VGI structured data that is integrated in the Linked OpenData cloud. This new database will support data quality control during the acquisition of information and assist data retrieval, in order to improve the quality of Volunteered Geographic Information.