Exploring place through user-generated content: Using Flickr tags to describe city cores

By Livia Hollenstein, Ross S. Purves. J. Spatial Inf. Sci., 2010

480 citations recorded by the source corpus.

Terms used to describe city centers, such as Downtown, are key concepts in everyday or vernacular language. Here, we explore such language by harvesting georeferenced and tagged metadata associated with 8 million Flickr images and thus consider how large numbers of people name city core areas. The nature of errors and imprecision in tagging and georeferencing are quantified, and automatically generated precision measures appear to mirror errors in the positioning of images. Users seek to ascribe appropriate semantics to images, though bulk-uploading and bulk-tagging may introduce bias. Between 0.5–2% of tags associated with georeferenced images analyzed describe city core areas generically, while 70% of all georeferenced images analyzed include specific place name tags, with place names at the granularity of city names being by far the most common. Using Flickr metadata, it is possible not only to describe the use of the term Downtown across the USA, but also to explore the borders of city center neighborhoods at the level of individual cities, whilst accounting for bias by the use of tag profiles.

Subfields: Computer Vision and Pattern Recognition, Geography, Planning and Development, Transportation

View Paper: https://www.semanticscholar.org/paper/55d92a4ab7af52d976834ecb259469cf397d40ce

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Geography, Planning and Development

In Transportation

Citations in the corpus

A review of volunteered geographic information quality assessment methods (2017, background): “This vagueness in human conceptualization of location is due not only to the fact that geographic entities are continuous in nature, but also due to the quality and limitations of spatial knowledge (Hollenstein and Purves 2010).”
Beyond the geotag: situating ‘big data’ and leveraging the potential of the geoweb (2013, background): “…examined through mapping the spatial contours of geo-coded internet information, including Google Maps place-marks (Graham and Zook 2011), Flickr photos (Hollenstein and Purves 2010; Wall and Kirdnark 2012), Wikipedia entries (Graham, Hale, and Stephens 2011) and, most recently, geocoded tweets.”
Extracting and understanding urban areas of interest using geotagged photos (2015, background): “As suggested by Hollenstein and Purves (2010), some active Flickr users have uploaded a large number of photos, while those less active users have only uploaded a few.”
Travelers’ food experience sharing on social network sites (2017, background): “UGC is generated and disseminated online by the general public, or users who are not paid professionals (Hollenstein & Purves, 2015).”
A visual analytics approach to understanding cycling behaviour (2012, unknown): “…chapter examines the relationship between two types of spatial presence: the spatial presence that articulates the audience’s suspension of disbelief and their subsequent location within a film’s narrative world, and the spatial presence of sound and music within a multichannel cinema environment.”
Spatial, temporal, and socioeconomic patterns in the use of Twitter and Flickr (2013, background): “For example, the location and spatial boundary of places may be delineated based on the aggregation of geotagged photos in Flickr (Hollenstein and Purves 2010; Li and Goodchild 2012).”