World explorer

TLDR

Map interfaces and location‑aware devices now expose vast amounts of unstructured, geo‑referenced data, such as the 20 million Flickr photos tagged by users, which can be leveraged for both browsing individual items and analyzing aggregate trends. The study demonstrates how to analyze Flickr photo tags to produce representative tags for any geographic area. The authors built World Explorer, a map‑based visualization that displays derived representative tags alongside the original Flickr photos, and qualitatively evaluated its usefulness for browsing such content. The evaluation revealed insights into how aggregate tag browsing differs from individual‑item browsing of geo‑referenced media.

Abstract

The availability of map interfaces and location-aware devices makes a growing amount of unstructured, geo-referenced information available on the Web. This type of information can be valuable not only for browsing, finding and making sense of individual items, but also in aggregate form to help understand data trends and features. In particular, over twenty million geo-referenced photos are now available on Flickr, a photo-sharing website - the first major collection of its kind. These photos are often associated with user-entered unstructured text labels (i.e., tags). We show how we analyze the tags associated with the geo-referenced Flickr images to generate aggregate knowledge in the form of "representative tags" for arbitrary areas in the world. We use these tags to create a visualization tool, World Explorer, tha tcan help expose the content of the data, using a map interface to display the derived tags and the original photo items. We perform a qualitative evaluation of World Explorer that outlines the visualization's benefits in browsing this type of content. We provide insights regarding the aggregate versus individual-item requirements in browsing digital geo-referenced material.