An agent-based and quality-aware integration of geo-social networks data - data integration as a collaborative negotiation process

• Applicant: Professor Dr. Alexander Zipf
• Subject Area: Geodesy, Photogrammetry, Remote Sensing, Geoinformatics, Cartography ; Human Geography
• Term: from 2015 to 2020
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 276698709

• Final Report Year: 2020

Final Report Abstract

With the success of the Web 2.0 paradigm and the associated increase in the use of smartphones (equipped with position sensors), citizens are increasingly actively and passively producing valuable geographic information about places, here referred as POIs, in volunteered geographic information platforms and geo-social networks. The information contained in these platforms offer significant potential for leveraging existing and new geospatial applications relevant to society. However, because this geographic information is dispersed across different sources, each with its purposes, group of contributors, data characteristics, etc., approaches need to be developed for integrating this heterogeneous information and accounting for the issue of data quality. This project has set this as its goal contributing to covering this research gap. Furthermore, it attempted to relate the aspects of data integration and quality as dependent on the contributors’ profile (background, interests, expertise, etc.) and model this interplay through simulations based on empirical data. Different approaches based on graph-theory principles for integrating data from VGI and social media platforms were conceived, implemented and tested. However, due to persisting and imposed limitations on the access to the users’ profile information, we were obliged to adapt early approaches and, instead, estimate the reliability of geographic data from social media from the consistency of the user community and user-defined concepts (i.e. tags) associated to the posts, which has proven to be successful. The graph-based geo-data integration approach developed during this project found direct application in the system for the generation of pleasant pedestrian routes. In accordance with the open data principle and for the sake of reproducibility, our geo-data integration approach is available at a code sharing platform.

Publications

• (2016) Defining fitness-for-use for crowdsourced points of interest (POI). ISPRS International Journal of Geo-Information. Vol. 5, p. 149–149
  Jonietz, D. and Zipf, A.
  (See online at https://doi.org/10.3390/ijgi5090149)
• (2017) Graph-based strategies for matching points-of-interests from different VGI sources. In: Proceedings of the 20th AGILE Conference. Wageningen (Holland)
  Novack, T., Peters, R., Zipf, A.
  
• (2017): Highlighting Current Trends in Volunteered Geographic Information. International Journal of Geo-Information. 2017, 6(7), 202
  Jonietz, D., Antonio, V., See, L., Zipf, A.
  (See online at https://doi.org/10.3390/ijgi6070202)
• (2018) Coupling maximum entropy modeling with geotagged social media data to determine the geographic distribution of tourists. International Journal of Geographical Information Science (IJGIS)
  Yan, Y. C.-L. Kuo, C.-C. Feng, W. Huang, H. Fan & A. Zipf
  (See online at https://doi.org/10.1080/13658816.2018.1458989)
• (2018): A System for Generating Customized Pleasant Pedestrian Routes Based on OpenStreetMap Data. Sensors, Vol. 18, 3794
  Novack, T., Wang, Z., Zipf, A.
  (See online at https://doi.org/10.3390/s18113794)
• (2018): Efficient Method for POI/ROI Discovery Using Flickr Geotagged Photos. ISPRS Int. J. Geo-Inf. 2018, 7(3), 121
  Kuo, C.-L., T.C. Chan, I.-C. Fan, A. Zipf
  (See online at https://doi.org/10.3390/ijgi7030121)
• (2018): Graph-Based Matching of Points-of-Interest from Collaborative Geo-Datasets. International Journal of Geo-Information, Vol. 7 (3), pp. 117-134
  Novack, T., Peters, R., Zipf, A.
  (See online at https://doi.org/10.3390/ijgi7030117)
• (2019) Open-data-driven embeddable quality management services for map-based web applications. Big Earth Data, 2:4, 395-422, 2019
  Noskov, A. and Zipf, A.
  (See online at https://doi.org/10.1080/20964471.2019.1592077)
• (2019). Exploring the effects of Pokémon Go vandalism on OpenStreetMap. In: Proceedings of the Academic Track at the State of the Map 2019. Heidelberg (Germany)
  Juhász, L., Hochmair, H.H., Qiao, S., Novack, T.
  (See online at https://doi.org/10.5281/zenodo.3386533)
• (2019). The geographical and cultural aspects of geo-information: an introduction. In: Proceedings of the GeoCultGIS - Geographical and Cultural Aspects of Geo-Information: Issues and Solutions. Limassol (Cyprus)
  Novack, T., Grinberger, A.Y., Schultz, M., Zipf, A., Mooney, P.
  (See online at https://doi.org/10.11588/heidok.00027406)
• (2019): An exploratory analysis of usability of Flickr tags for land use/land cover attribution, Geo-spatial Information Science (GSIS)
  Yan, Y., Schultz, M., Zipf, A.
  (See online at https://doi.org/10.1080/10095020.2018.1560044)
• (2019): Towards Detecting Building Facades With Graffiti Artwork Based on Street View Imagery. International Journal of Geo-Information, 9, 98
  Novack, T., Vorbeck, L., Lorei, H., Zipf, A.
  (See online at https://doi.org/10.3390/ijgi9020098)
• (2020): Towards Detecting Building Facades With Graffiti Artwork Based on Street View Imagery. Int. Journal of Geo-Information, 9, 98
  Novack, T., Vorbeck, L., Lorei, H., Zipf, A.
  (See online at https://doi.org/10.3390/ijgi9020098)