Automatic analysis of positional plausibility for points of interest in OpenStreetMap using coexistence patterns

ABSTRACT

In the past decade, Volunteered Geographic Information (VGI) has emerged as a new source of geographic information, making it a cheap and universal competitor to existing authoritative data sources. The growing popularity of VGI platforms, such as OpenStreetMap (OSM), would trigger malicious activities such as vandalism or spam. Similarly, wrong entries by unexperienced contributors adds to the complexities and directly impact the reliability of such databases. While there are some existing methods and tools for monitoring OSM data quality, there is still a lack of advanced mechanisms for automatic validation. This paper presents a new recommender tool which evaluates the positional plausibility of incoming POI registrations in OSM by generating near real-time validation scores. Similar to machine learning techniques, the tool discovers, stores and reapplies binary distance-based coexistence patterns between one specific POI and its surrounding objects. To clarify the idea, basic concepts about analysing coexistence patterns including design methodology and algorithms are covered in this context. Furthermore, the results of two case studies are presented to demonstrate the analytical power and reliability of the proposed technique. The encouraging results of this new recommendation tool elevates the need for developing reliable quality assurance systems in OSM and other VGI projects.

KEYWORDS:

• OSM
• coexistence patterns
• spatial data quality
• spatial association rules
• spatial data mining
• points of interest

Acknowledgments

We would like to thank the Centre of Disaster Management and Public Safety (CDMPS) at the University of Melbourne for supporting this research.

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1. Java OpenStreetMap Editor [online]. Available from: https://josm.openstreetmap.de [Accessed 8 September 2017].

2. Basic components of OpenStreetMap’s conceptual data model [online]. Available from: http://wiki.openstreetmap.org/wiki/Elements [Accessed 8 September 2017].

3. Google Maps [online]. Available from: http://map.google.com [Accessed 9 September 2017].

4. Yelp [online]. Available from: https://www.yelp.com [Accessed 9 September 2017].

5. Foursquare [online]. Available from: https://foursquare.com [Accessed 9 September 2017].

6. iD: OpenStreetMap editor programmed in JavaScript [online]. Available from: http://wiki.openstreetmap.org/wiki/ID [Accessed 9 September 2017].

7. Potlatch 2: OpenStreetMap editor known as P2 [online]. Available from: http://wiki.openstreetmap.org/wiki/Potlatch_2 [Accessed 9 September 2017].

8. OpenStreetMap Quality Assurance [online]. Available from: http://wiki.openstreetmap.org/wiki/Quality_assurance [Accessed 9 September 2017].

9. Linkedgeodata [online]. Available from: http://linkedgeodata.org [Accessed 9 September 2017].

10. DBpedia: Towards a Public Data Infrastructure for a Large, Multilingual, Semantic Knowledge Graph [online]. Available from: http://wiki.dbpedia.org [Accessed 9 September 2017].

11. GeoNames [online]. Available from: http://www.geonames.org/ [Accessed 9 September 2017].

12. BBBike: Cycle route planner [online]. Available from: https://download.bbbike.org/osm/bbbike/ [Accessed 9 September 2017].

13. Since the platform is under active development new features and methods might have been added at the time of reading this paper.

Additional information

Notes on contributors

Alireza Kashian

Alireza Kashian, is Ph.d student at the University of Melbourne and works as a researcher at the Centre for Disaster Management & Public Safety. As a serial entrepreneur, he has wide range of experiences in mapping technologies, automatic cartography, telematics and location intelligence. Topics such as geographic crowdsourcing, spatial data mining and artificial intelligence is among his academic interests.  He is currently developing new colocation mining algorithms to analyse urban context for ultra-fast address and location queries.

Abbas Rajabifard

Prof Abbas Rajabifard, is Director of the Centre for Spatial Data Infrastructures & Land Administration at The University of Melbourne, Australia. He is also Chair of United Nations Global Geospatial Information Management Academic Network (UN-GGIM), which is a strategic research and training arm for UN-GGIM.

Kai-Florian Richter

Kai-Florian Richter, is an Associate Professor at the Department of Computing Science at Umeå University, Sweden. His research is interdisciplinary and set in the interface between artificial intelligence, human-computer interaction, cognitive science, and geographic information science. Using a cognitive engineering approach, his research focuses on cognitive aspects of interaction between humans and autonomous systems, with the particular aim to close or shorten the communication and concept gap between human and machine in their interactions.

Yiqun Chen

Yiqun Chen, received his Ph.D degree at the University of Melbourne in 2013. He currently is a research fellow working at the Centre for Disaster Management & Public Safety at the University of Melbourne. His research interests include GIS visualisation, spatial analysis, disaster management and agent-based modelling.