This article from David Crandall et.al at Cornell University may be of interest. An historian asked me the other day what were the majore concerns of the Digital Humanities. I tried to explain that once there is a lot of data; like all the books in the 19th Century being in digital form, or all the court records of the Old Bailey for 200 years, or millions of digitised books within the Google Books project, then things start to get interesting. This is one such project. Although the research question may not be that imaginative, the method of finding it out holds much promise for other applications. Here is the paper:
We investigate how to organize a large collection of geotagged photos, working with a dataset of about 35 million images collected from Flickr. Our approach combines content analysis based on text tags and image data with structural analysis based on geospatial data. We use the spatial distribution of where people take photos to define a relational structure between the photos that are taken at popular places. We then study the interplay between this structure and the content, using classification methods for predicting such locations from visual, textual and temporal features of the photos. We find that visual and temporal features improve the ability to estimate the location of a photo, compared to using just textual features. We illustrate using these techniques to organize a large photo collection, while also revealing various interesting properties about popular cities and landmarks at a global scale (link).
(A photo from Flikr. This is Eiffel’s Bridge in Porto. I stood on this on the weekend. This may not be one of the world’s most popular places to photograph, but who cares!)
