Semantic enrichment of places: Ontology learning from web

Abstract

In this paper, we present an approach to a challenge well known from the area of Ubiquitous Computing: extracting meaning out of geo-referenced information. We believe that Public Places can also be an environment where users can be confronted with intelligent services depending on their needs. To make this a reality we need firstly an intelligent way to represent places. The importance of this "semantics of place" problem is proportional to the number of available services and data that are common nowadays. Having rich knowledge about a place, we open up a new realm of "Location Based Services" that can behave more intelligently. Our approach builds on Ontology Engineering techniques in order to build a network of semantic associations between a place and related concepts. We briefly describe the KUSCO system and present some preliminary results.