A multi-scale approach to exploring urban places in geotagged photographs

A methodological toolbox for exploring collections of textually annotated georeferenced photographs

“…To capture notions of scale it is important to characterise tag semantics at multiple scales (c.f. Ahern et al 2007;Feick & Robertson 2014;Rattenbury & Naaman 2009). Dealing with MAUP has led to a number of approaches.…”

“…The basic effect of geographical applications of tf-idf is to privilege locally common, but globally rare tags over globally common tags. Recognising the nature of user generated content and the issues relating to user behaviour described above, many researchers have added a term to capture user frequency in this characterisation, typically ranking tags used by many higher within in a region (Ahern et al 2007;Feick & Obviously the size and form of the regions within which frequencies are calculated will have an influence on the results. The former property, size effectively captures notions of scale, while the latter, form, is closely related to the classical Modifiable Areal Unit Problem (MAUP).…”

“…• Automatic generation of gazetteer data (Kessler et al 2009) • Extraction and delineation of vernacular place names (Hollenstein & Purves 2010) • Tag recommendations for images based on location (Rattenbury & Naaman 2009) • Adding information to existing spatial databases (Antoniou et al 2010) • Extraction of place semantics at a range of scales (Feick & Robertson 2014;Purves et al 2011;Rattenbury & Naaman 2009) • Summarising and aggregating properties of the semantics of space (Ahern et al 2007;Dykes & Wood 2009;Purves et al 2011) • Exploring movement of groups of individuals in space (Girardin et al 2008) • Identification and prediction of locations in text (O'Hare & Murdock 2012) • Extraction of events using space-time clustering (Andrienko et al 2010) All of these approaches require methods which go beyond analysing spatial patterns associated only with the locations of photographs. This is the province of an established toolbox of geostatistical techniques for point pattern analysis able to describe spatial distributions and multi-scale patterns (O'Sullivan & Unwin 2003: chap.…”

Tagging in Volunteered Geographic Information: An Analysis of Tagging Practices for Cities and Urban Regions in OpenStreetMap

“…One of the reasons for this is the fact that the OSM tagging structure is a very flexible and open folksonomy approach. In work by [23], the authors demonstrate a method for analyzing tag frequency using Flickr data obtained for the city of Vancouver, Canada. They argue that tag characteristics depend on the spatial scale of aggregation.…”

A Simple Tags Categorization Framework Using Spatial Coverage to Discover Geospatial Semantics

“…It suggests that traditional clustering and aggregation methods used to discover spatial semantics and knowledge are not appropriate in other places, where the density of images is low. In [4] Flickr tags are aggregated at multiple scales to study their spatial and thematic properties. The study confirms that for sources like Flickr, tags are clustered in touristic and entertainment areas.…”