Abstract
It is known that geography-aware keyword queries correspond to a significant share of the users' demand on search engines. This paper describes a strategy for tagging documents with place names according to the geographical context of their textual content by using a topic indexing technique that considers Wikipedia articles as a controlled vocabulary. By identifying those topics in the text, we connect documents with the Wiki-pedia semantic network of articles allowing us to perform operations on Wikipedia's graph and find related places. We present an experimental evaluation on documents tagged as Brazilian states demonstrating the feasibility of our proposal and opening the way to further research geotagging based on semantic networks. © Springer-Verlag Berlin Heidelberg 2011.
Cite
CITATION STYLE
De Alencar, R. O., & Davis, C. A. (2011). Geotagging aided by topic detection with Wikipedia. In Lecture Notes in Geoinformation and Cartography (pp. 461–477). Kluwer Academic Publishers. https://doi.org/10.1007/978-3-642-19789-5_23
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
