| ||||
David Wilson: AbstractVolunteered geographic information (VGI) is generated by heterogenous ‘information communities’ that co-operate to produce reusable units of geographic knowledge. A consensual lexicon is a key factor to enable this open production model. Lexical definitions help demarcate the boundaries of terms, forming a thin semantic ground on which knowledge can travel. In VGI, lexical definitions often appear to be inconsistent, circular, noisy, and highly idiosyncratic. Computing the semantic similarity of these ‘volunteered lexical definitions’ has a wide range of applications in GIScience, including information retrieval and information integration. This talk presents the development and evaluation of an approach to mine the semantic similarity of geographic terms in VGI by focusing exclusively their lexical definitions. In turn, the mined geographic knowledge provides a foundation for software tools to support more effective use of and interaction with VGI data.
|
||||
