Acquisition of Vernacular Place Names from Web Sources

Abstract

Vernacular place names are names that are commonly in use to refer to geographical places. For purposes of effective information retrieval, the spatial extent associated with these names should reflect peoples perception of the place, even though this may differ sometimes from the administrative definition of the same place name. Due to their informal nature, vernacular place names are hard to capture, but methods to acquire and define vernacular place names are of great benefit to search engines and all kinds of information services that deal with geographic data. This paper discusses the acquisition of vernacular use of place names from web sources and their representation as surface models derived by kernel density estimators. We show that various web sources containing user created geographic information and business data can be used to represent neighbourhoods in Cardiff, UK. The resulting representations can differ in their spatial extent from administrative definitions. The chapter closes with an outlook on future research questions.

Automatic gazetteer enrichment with user-geocoded data

“…Others have mined places with their geographical extent from web pages [3], or mined places and determined their geographical extent from references such as postal code [32], or through a specially made tool such as the Jeocrowd to search user-generated data sets [19]. Others have asked users to help generate place names by setting up a separate web platform and asking people to add place names directly [31], or asking users to photograph every kilometer of the earth's surface and mine the place name tags indirectly, in the Geograph project 3 .…”

A Geo-Clustering Approach for the Detection of Areas-of-Interest and Their Underlying Semantics

“…Earlier approaches exploited available geolocation services and user-generated tags, while more recent ones have focused on the socially-generated geo-tagged metadata from popular social networking websites. Amongst the most characteristic approaches of the first category is the one of Twaroch et al [16], who reviewed efforts towards the extraction of knowledge on vernacular places before the rising of geo-tagging. Current methods included mining the web, using geo-references from business directories, from social websites or from user created information sources.…”

A data driven approach to mapping urban neighbourhoods

“…The quadratic KDE measures used here rely on a cell size of 50m and utilise two different search radii: 300m (as commonly used within the literature [10,12]) and 1600m (to gauge overall mass at a larger geographic scale). Unlike previous works which at this point produce a single KDE surface of point data for each neighbourhood, we constructed a number of KDE based computational rules to further reduce noise.…”

“…One criticism of the KDE approach is that it has a tendency to over-smooth (especially at the edges) and to help compensate for this a 2% cut-off is applied to "trim the edges' [12].…”

“…Even in the UK, where some gazetteers provide single geospatial points of reference for neighbourhoods, data are often incomplete and rarely agree [2]. In the absence of neighbourhood boundary definitions, many social studies have therefore had to resort to using official administrative units (formal areas used by local and national government for statistical purposes) as proxies for neighbourhoods -despite the fact that these do not correspond to resident perceptions of boundaries, even when they have the same name [9,12].…”