TY - GEN
T1 - Annotating geographical objects in OpenStreetMap with geo-tagged social media
AU - Chen, Xin
AU - Vo, Hoang
AU - Wang, Fusheng
N1 - Publisher Copyright:
© ACM 2016.
PY - 2016/10/31
Y1 - 2016/10/31
N2 - Recent years have witnessed an explosion of geospatial data, especially in the form of Volunteered Geographic Informa-tion (VGI). As a prominent example, OpenStreetMap (OSM) creates a free editable map of the world from a large number of contributors. On the other hand, social media platforms such as Twitter or Instagram supply dynamic social feeds at population level. As much of such data is geo-tagged, there is a high potential on integrating social media with OSM to enrich OSM with semantic annotations, which will comple-ment existing objective description oriented annotations to provide a broader range of annotations. In this paper, we propose a comprehensive framework on integrating social media data and VGI data to derive knowledge about geo-graphical objects, specifically, top relevant annotations from tweets for objects in OSM. We first integrate geo-tagged tweets with OSM data with scalable spatial queries running on MapReduce. We propose a frequency based method for annotating boundary based geographic objects, and a prob-ability based method for annotating point based geographic objects, with consideration of noise. We evaluate our meth-ods using a large geo-tagged tweets corpus and represen-tative geographic objects from OSM, which demonstrates promising results through ground-truth comparison and case studies. We are able to produce up to 80% correct names for geographical objects and discover implicitly relevant in-formation, such as popular exhibitions of a museum, the nicknames or visitors' impression to a tourism attraction.
AB - Recent years have witnessed an explosion of geospatial data, especially in the form of Volunteered Geographic Informa-tion (VGI). As a prominent example, OpenStreetMap (OSM) creates a free editable map of the world from a large number of contributors. On the other hand, social media platforms such as Twitter or Instagram supply dynamic social feeds at population level. As much of such data is geo-tagged, there is a high potential on integrating social media with OSM to enrich OSM with semantic annotations, which will comple-ment existing objective description oriented annotations to provide a broader range of annotations. In this paper, we propose a comprehensive framework on integrating social media data and VGI data to derive knowledge about geo-graphical objects, specifically, top relevant annotations from tweets for objects in OSM. We first integrate geo-tagged tweets with OSM data with scalable spatial queries running on MapReduce. We propose a frequency based method for annotating boundary based geographic objects, and a prob-ability based method for annotating point based geographic objects, with consideration of noise. We evaluate our meth-ods using a large geo-tagged tweets corpus and represen-tative geographic objects from OSM, which demonstrates promising results through ground-truth comparison and case studies. We are able to produce up to 80% correct names for geographical objects and discover implicitly relevant in-formation, such as popular exhibitions of a museum, the nicknames or visitors' impression to a tourism attraction.
UR - https://www.scopus.com/pages/publications/85020003498
U2 - 10.1145/3021304.3021306
DO - 10.1145/3021304.3021306
M3 - Conference contribution
AN - SCOPUS:85020003498
T3 - Proceedings of the 9th ACM SIGSPATIAL Workshop on Location-Based Social Networks, LBSN 2016
BT - Proceedings of the 9th ACM SIGSPATIAL Workshop on Location-Based Social Networks, LBSN 2016
PB - Association for Computing Machinery, Inc
T2 - 9th ACM SIGSPATIAL Workshop on Location-Based Social Networks, LBSN 2016
Y2 - 31 October 2016 through 3 November 2016
ER -