Geographic Information Retrieval: Progress and Challenges in Spatial Search of Text

Abstract

Significant amounts of information available today contain references to places on earth. Traditionally such information has been held as structured data and was the concern of Geographic Information Systems (GIS). However, increasing amounts of data in the form of unstructured text are available for indexing and retrieval that also contain spatial references. This monograph describes the field of Geographic Information Retrieval (GIR) that seeks to develop spatially-aware search systems and support user's geographical information needs. Important concepts with respect to storing, querying and analysing geographical information in computers are introduced, before user needs and interaction in the context of GIR are explored. The task of associating documents with coordinates, prior to their indexing and ranking forms the core of any GIR system, and different approaches and their implications are discussed. Evaluating the resulting systems and their components, and different paradigms for doing so continue to be an important area of research in GIR and are illustrated through a number of examples. The article concludes by setting out a range of future challenges for research in this field.

Spatial search strategies for open government data

“…Besides, Table 7 suggests that (iii) Hausdorff distance as spatial similarity metric produces slightly better results than area of overlap (s6 and s7 left aside) from the user's viewpoint. As regards the method, previous work has indicated that a "challenge for future research in GIR, and more particularly georeferencing, is reproducible publishing of methods, algorithms, datasets, and results such that approaches can be more easily compared across corpora" ( [53], emphasis added). The method used in this work has involved two key steps towards a holistic assessment of spatial search strategies, namely performance-based and user-based assessment.…”

A Review of Geospatial Semantic Information Modeling and Elicitation Approaches

“…Geographic information retrieval (GIR) [142,143] is another relevant field which deals with the automated interpretation of place names and spatial relationships in queries and in documents and with indexing, relevance ranking, and retrieval of the relevant content. GIR faces significant challenges such as detecting geographical references and associated spatial natural language qualifiers, disambiguating place names or other geographic information, and ranking resources with respect to spatial, temporal, and thematic relevance.…”

Text Meets Space: Geographic Content Extraction, Resolution and Information Retrieval

“…-students of computer science, especially in information retrieval, who want to learn about mobility-relevant spatial computation around search/IR (e.g. [2]); -practicing IR engineers who would like to expand their areas of expertise so as to include geographic search; -information retrieval researchers interested in and introduction and state-ofthe-art review [14] on GIR and Geo-NLP; -geographers or GIS experts who have not yet worked with text, and who would like to learn how the spatial knowledge implicit in text collections can be used to support geospatial analysis.…”

“…Together with Chris Jones, he organises the workshop on Geographic Information Retrieval which has been hosted by CIKM, SIGIR and ACM SIGSPATIAL, and which has been an important incubator of many ideas related to GIR. He recently co-authored a comprehensive review of GIR [14].…”