A tool for exploring the tempo-spatial distribution of Flickr tags

• Main Author: Rodas Rivera, Juan L.
• Other Authors: Woodhouse, Iain H.
• Format: Master Thesis
• Language: English
• Published: The University of Edinburgh 2014
• Subjects: flickr; tags; tempo-spatial querying; metadata; vgi; clustering; dbscan; postgis; MSc Geographical Information Science; GIS; Pacific; Humpback Whale
• Online Access: http://hdl.handle.net/1842/10352

Social networks and modern age connectivity generate large amounts of data every day. Some of these datasets contain geographical information which could potentially be used to perform spatial or temporal analysis. In this paper a tool is introduced with the aims to allow tempo-spatial exploration on photos downloaded from the photo sharing site Flickr. The tool is built on PHP and JavaScript and uses PostgreSQL as a data store with PostGIS for spatial data processing, WMS and WFS services are provided by GeoServer. The tool first connects to the Flickr public API REST endpoint to download the photos which are related to a specific tag requested by the user. Preprocessing is performed on the downloaded dataset to remove multiple photos that have been taken by the user on the same location on the same day. Cluster analysis is performed on the reduced dataset once for each time unit on a specified study area using the DBSCAN density-based algorithm. Quadrat count analysis is performed by the tool as the last step in the process, giving the user the statistical means to assess the validity of the cluster analysis. The tool is evaluated on the last section of this paper with a case study that uses a dataset comprising photos with the “humpback whale” tag. This dataset is used to find the location of the most popular whale watching spots for four study areas in the North Pacific Ocean. The results are evaluated to assess the spots chosen by the tool.