Abstract. The SPIRIT search engine provides a test bed for the development of web search technology that is specialised for access to geographical information. Major components include the user interface, geographical ontology, maintenance and retrieval functions for a test collection of web documents, textual and spatial indexes, relevance ranking and metadata extraction. Here we summarise the functionality and interaction between these components before focusing on the design of the geo-ontology and the development of spatio-textual indexing methods. The geo-ontology supports functionality for disambiguation, query expansion, relevance ranking and metadata extraction. Geographical place names are accompanied by multiple geometric footprints and qualitative spatial relationships. Spatial indexing of documents has been integrated with text indexing through the use of spatio-textual keys in which terms are concatenated with spatial cells to which they relate. Preliminary experiments demonstrate considerable performance benefits when compared with pure text indexing and with text indexing followed by a spatial filtering stage. 1

Abstract. Geographical information exists in multiple forms such as cartographical maps, images, and texts. Effective retrieval systems for geographical information are currently studied by both geospatial information scientists and library/information scientists. The two groups take quite different approaches which have rarely been explicitly compared and connected. This paper discusses the advantages and limitations of current geographical information retrieval (GIR) and textual information retrieval (IR) systems in dealing with multimedia geographical information, and proposes a new retrieval model, called GeoVSM (Geographical + Vector Space Model), which integrates coordinate-based geographical indexing with keyword-based vector space model in representing information space. Document ranking by relevance is supported by document-query similarity measure taking into account degree of relevance in both spatial domain and thematic domain. To support visual query and browsing, GeoVSM model recognizes the fundamental differences in the dimensionality and configuration of geographical space and thematic space, and demands multi-view visual interfaces based on a “world ” metaphor and a “desktop ” metaphor. As an example of such interfaces, GeoVIBE is presented that supports a coordinated GeoView and a VibeView for smooth integration of two browsing strategies using geographic clues as well as thematic clues provided by users. 1.

Geographic knowledge is essential in handling a large variety of resources, including cultural contents such as museum artifacts, maps, books, photographs, and videos. The metadata of such resources often need to refer to a geographic entity or region, for example to the place where an artifact was produced, used, or found. In this paper, we examine how geographical knowledge may be represented ontologically to enable different types of searches, visualization, and inference in cultural semantic portals and other semantic geo-applications. In particular, we show how change in time between historical regions can be explicated as an ontology and be used for reasoning. Regarding search and visualization, we show how maps of different time periods can be visualized as transparent overlays on top of Google Maps, how cultural content can be visualized on them, how geo-based queries can be formulated based on maps, and how additional services, such as a meta-search system, can be integrated in the mash-up system. The work presented is being integrated at the practical level in the cultural semantic cross-domain portal CultureSampo.

All aspects of human activity are rooted in geographic space in some respect. As a consequence, many web resources include references to geographic context. In order to assist in recognising spatial terms employed in a query, it is proposed to use a geographical ontology. A geo-ontology play a key role in the development of spatially-aware search engine, with regards to providing support for query disambiguation, query expansion, relevance ranking and web resource annotation. This paper describes the geo-ontology designed for the SPIRIT system, before focussing on the problem of integrating multiple datasets for constructing such an ontology. Similarity checking of datasets is an essential step in the process of integration. The validity and effect of the different measures are studied by building a prototype geo-ontology utilising different datasets. The experimental results obtained confirmed the effect of quality of the datasets and the importance of the flexibility of the technique proposed for adjusting the similarity measures to handle such an effect.

Abstract. Many types of information are geographically referenced and interactive maps provide a natural user interface to such data. However, map presentation in geographical information systems (GIS) and on the internet is closely related to traditional cartography and provides a very limited interactive experience. We present the MAPBOT, a web-based map information retrieval system to search geographical information using software agent techniques. Each kind of map feature such as a building or a road is treated as an agent called a Maplet. Each Maplet has a user interface level to assist the user to find information of interest and a graphic display level that controls the presence and the appearance of the feature on the map. Semantic relationships of Maplets are defined in an Ontology Repository (OR) and used to control their retrieval. To allow system developers to manipulate the OR, an Ontology Editor is implemented with a graphical user interface. Visualisation on the client is based on Scalable Vector Graphics (SVG). The paper describes the current state of development of the prototype and presents, and evaluates experimentally, an agent-oriented graphical conflict resolution procedure, which demonstrates the potential for conflict resolution via low level agent communication, as opposed to global control. 1.

We present the results of a case study aiming to assess whether the reflection of the physical environment in the Web is usable to enhance navigation services. The wealth of information contained in Web resources consists of its content, as well as of the semantics in its patterns. We analyze the possibility to improve the navigation services beyond simple provision of landmarks. We are assessing the suitability of the Web documents to provide supporting information for an automated urban navigation service, through the reconstruction of the semantics of georeferences in Web resources to scenes. We argue that this eases the wayfinder’s cognitive load necessary to remember the set of route directions and to navigate in the environment. In a detailed analysis of the Web resources we identify usable patterns and ways to mine the information out of these patterns. We show how the interpretation of georeferences in Web resources reflects perceivable properties of described features.

In this paper we examine 1) the scope of geo-ontologies used especially for the purposes of information retrieval on the Web, 2) the core geographical concepts and their mutual relations, and 3) the properties the concepts have. Furthermore, we present the Finnish geo-ontology (Suomalainen paikkaontologia, SUO) and discuss the theories and principles that have governed the development process, as well as the limitations and requirements the use of geographical dictionaries as an instance data source have imposed to the content and the structure of SUO.

We describe an approach for extracting semantics for tags, unstructured text-labels assigned to resources on the Web, based on each tag’s usage patterns. In particular, we focus on the problem of extracting place semantics for tags that are assigned to photos on Flickr, a popular-photo sharing Web site that supports location (latitude/longitude) metadata for photos. We propose the adaptation of two baseline methods, inspired by well-known burst-analysis techniques, for the task; we also describe two novel methods, TagMaps and scale-structure identification. We evaluate the methods on a subset of Flickr data. We show that our scale-structure identification method outperforms existing techniques and that a hybrid approach generates further improvements (achieving 85% precision at 81 % recall). The approach and methods described in this work can be used in other domains such as geo-annotated Web pages, where text terms can be extracted and associated with usage patterns.

Mobile cartography aims at producing appropriate presentations of geographic information for mobile users, for instance in the form of map based mobile services. Major influences come from new technologies like Location Based Services. Due to the small displays of mobile devices and specific mobile usage contexts selecting and presenting only the most relevant information is indispensable. The paper argues for considering further relevance types beyond positional relevance used in LBS. First general theories of relevance are discussed before showing the use of the relevance concept in mobile cartography. Based on the relation between mobile usage context and relevance a set of relevance types is derived. Approaches for computing compound relevance measures enable applying the relevance as a filtering criterion or as an attribute that can be visualised. Various graphical means for visualising differences in relevance demonstrate the practical use of relevance measures in mobile cartography and represent a point of departure for further research.

A digital library typically includes a set of keywords (or subject terms) for each document in its collection(s). For some applications, including natural resource management, geographic location (e.g., the place of a study or a project) is very important. The metadata for such documents needs to indicate the location(s) associated with a document - and users need to be able to search for documents by keyword as well as location. We have developed and implemented a digital library that supports -- but does not require - georeferenceable documents (i.e., documents with reference to geography through the use of a textual place name). Because of their implicit spatial footprint, place names benefit from spatial reasoning and querying (e.g., to find all documents that describe work performed within a five-mile radius of a certain point) in addition to traditional keyword-based search. This paper presents the architecture for a digital library that combines spatial reasoning and selection with traditional (non-spatial) search. The contributions of this work are: (1) the use of a traditional geographic information system (GIS) for spatial processing rather than a specially tailored GIS system or a separate gazetteer and (2) the seamless integration of GIS with our thesaurus-based Metadata++ system, so users can easily take advantage of the strengths of both systems.