Geographic Information Retrieval

Geographical context is required of many information retrieval tasks in which the target of the search may be documents, images or records which are referenced to geographical space only by means of place names. Often there may be an imprecise match between the query name and the names associated with candidate sources of information. There is a need therefore for geographical information retrieval facilities that can rank the relevance of candidate information with respect to geographical closeness as well as semantic closeness with respect to the topic of interest. Here we present an ontology of place that combines limited coordinate data with qualitative spatial relationships between places. This parsimonious model of place is intended to support information retrieval tasks that may be global in scope. The ontology has been implemented with a semantic modelling system linking non-spatial conceptual hierarchies with the place ontology. An hierarchical distance measure is combined with Euclidean distance between place centroids to create a hybrid spatial distance measure. This can be combined with thematic distance, based on classification semantics, to create an integrated semantic closeness measure that can be used for a relevance ranking of retrieved objects.

Much of the information stored on the web contains geographical context, but current search engines treat such context in the same way as all other content. In this paper the design, implementation and evaluation of a spatially-aware search engine are described which is capable of handling queries in the form of the triplet of <theme><spatial relationship><location>. The process of identifying geographic references in documents and assigning appropriate footprints to documents, to be stored together with document terms in an appropriate indexing structure allowing real-time search is described. Methods allowing users to query and explore results which have been relevance ranked in terms of both thematic and spatial relevance have been implanted and a usability study indicates that users are happy with the range of spatial relationships available and intuitively understand how to use such a search engine. Normalised precision for 38 queries, containing four types of spatial relationships is significantly higher (p < 0.001) for search exploiting spatial information than pure text search. place name. However, such geographic terms are treated by conventional search engines in the same way as other terms and thus important semantic information is potentially discarded.

Gazeteers and geographical thesauri can be regarded as parsimonious spatial models that associate geographical location with place names and encode some semantic relations between the names. They are of particular value in processing information retrieval requests in which the user employs place names to specify geographical context. Typically the geometric locational data in a gazetteer are con ned to a simple footprint in the form of a centroid or a minimum bounding rectangle, both of which can be used to link to a map but are of limited value in determining spatial relationships. Here we describe a Voronoi diagram method for generating approximate regional extents from sets of centroids that are respectively inside and external to a region. The resulting approximations provide measures of areal extent and can be used to assist in answering geographical queries by evaluating spatial relationships such as distance, direction and common boundary length. Preliminary experimental evaluations of the method have been performed in the context of a semantic modelling system that combines the centroid data with hierarchical and adjacency relations between the associated place names.

This paper reports on the development and application of strategies and tools for geographic information seeking and knowledge building that leverages unstructured text resources found on the web. Geographic knowledge building from unstructured web sources starts with web document foraging during which the quantity, scope and diversity of web-based information create incredible cognitive burdens on an analyst"s or researcher"s ability to judge information relevancy. Determining information relevancy is ultimately a process of sensemaking. In this paper, we present our research on visually supporting web document foraging and sensemaking. In particular, we present the Senseof-Place (SensePlace) analytic environment. The scientific goal of SensePlace is to visually and computationally support analyst sensemaking with text artifacts that have potential place, time, and thematic relevance to an analytical problem through identification and visual highlighting of named entities (people, places, times, and organizations) in documents, automated inference to determine document relevance using stored knowledge, and a visual interface with coupled geographic map, timeline, and concept graph displays that are used to contextualize the contexts of potentially relevant documents. We present the results of a case study analysis using SensePlace to uncover potential population migration, geopolitical, and other infectious disease dynamics drivers for measles and other epidemics in Niger. Our analysis allowed us to demonstrate how our approach can support analysis of complex situations along (a) multi-scale geographic dimensions (i.e., vaccine coverage areas), (b) temporal dimensions (i.e., seasonal population movement and migrations), and (c) diverse thematic dimensions (effects of political upheaval, food security, transient movement, etc.).

How do people perceive landscapes? What elements of the landscape do they identify as characteristic of a landscape? And how can we arrive at descriptions, and ultimately representations that better reflect people’s notions of landscapes? In this study, we collected landscape descriptions from five landscape types at 10 study sites in Switzerland. For each site, we collected data from three sources: free lists with participants, hiking blogs, and Flickr tags. Free lists were obtained through on-site interviews with visitors, hiking blogs were gathered by focused crawling of web content, and Flickr tags were selected based on spatial footprints obtained from the hiking blogs. We quantitatively compared landscape descriptions between data sources and landscape types using cosine similarity. We found that descriptions from the same data source were significantly more similar, irrespective of landscape type. Descriptions from the same landscape type were more similar, but only within the same data source. Through a qualitative analysis of different aspects of landscape in our content, we found that each data source offered a different distribution of landscape aspects. For example, while Flickr tags contained high proportions of toponyms, they contained little content relating to sense of place. In contrast, hiking blogs contained more information about sense of place. Our approach combining these varied textual sources thus offers a more holistic view on landscapes. This study constitutes a step toward extracting semantically rich descriptions of landscapes from a variety of sources and using this information to distinguish different landscapes, with potential applications for landscape monitoring and management.

In this paper, we present a method for deriving an approximate spatial boundary for imprecise or vague geographical regions such the English Midlands. Geographic knowledge is crucial for any geographic information system (GIS) and often provided through gazetteers and geographical thesauri. However, these resources do not contain entries for vague regions even though common in natural language. We model spatial boundaries by deriving approximate polygon boundaries formed using geographic locations extracted from pages retrieved by searching the web. The method is evaluated using both precise and vague places and the approximate boundaries generated using this method can then be used within GIS, such as geographic IR systems. Results from using the web as a source of geographic knowledge for our approach are promising.

Spatial information takes different forms in different applications, ranging from accurate coordinates in geographic information systems to the qualitative abstractions that are used in artificial intelligence and spatial cognition. As a result, existing spatial information processing techniques tend to be tailored towards one type of spatial information, and cannot readily be extended to cope with the heterogeneity of spatial information that often arises in practice. In applications such as geographic information retrieval, on the other hand, approximate boundaries of spatial regions need to be constructed, using whatever spatial information that can be obtained. Motivated by this observation, we propose a novel methodology for generating spatial scenarios that are compatible with available knowledge. By suitably discretizing space, this task is translated to a combinatorial optimization problem, which is solved using a hybridization of two well-known meta-heuristics: genetic algorithms and ant colony optimization. What results is a flexible method that can cope with both quantitative and qualitative information, and can easily be adapted to the specific needs of specific applications. Experiments with geographic data demonstrate the potential of the approach. satisfaction problem (CSP), where the number of constraints is finite, but the domains of the variables, which could be instantiated by arbitrary polygons, 1 are infinite. Typical reasoning tasks of interest consist of checking whether a certain set of topological relations is consistent (or satisfiable), i.e. if there can actually exist polygons such that the given topological relations are all satisfied .

The selection and retrieval of relevant information from the information universe on the web is becoming increasingly important in addressing information overload. It has also been recognized that geography is an important criterion of relevance, leading to the research area of geographic information retrieval. As users increasingly retrieve information in mobile situations, relevance is often related to geographic features in the real world as well as their representation in web documents. We present 2 methods for assessing geographic relevance (GR) of geographic entities in a mobile use context that include the 5 criteria topicality, spatiotemporal proximity, directionality, cluster, and colocation. To determine the effectiveness and validity of these methods, we evaluate them through a user study conducted on the Amazon Mechanical Turk crowdsourcing platform. An analysis of relevance ranks for geographic entities in 3 scenarios produced by two GR methods, 2 baseline methods, and human judgments collected in the experiment reveal that one of the GR methods produces similar ranks as human assessors.

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.

In this paper, we introduce a geographic similarity operator that computes the relatedness between two geographic places and describe how it is combined with textual ranking. The effectiveness of the geographic ranking is evaluated on the GeoCLEF 2005 collection. We considered various strategies for query formulation and for combining textual ant geographical ranking. For some queries, geographic ranking significantly improves results, while for other queries it does not have a positive impact.

Gazetteers are important tools used in a wide variety of workflows that depend on linking natural language text to geographical space. The spatial properties of these data sources, such as coverage, balance, and completeness, affect the performance of common tasks such as geoparsing and geocoding. However, little attention has focused on how these properties vary in global gazetteers, particularly across country boundaries and according to feature types. In this paper, we present a detailed investigation of the spatial properties of two open gazetteers with worldwide coverage: GeoNames, and the Getty Thesaurus of Geographic Names (TGN). Using point density maps, correlations, and linear regressions, we analyze the global spatial coverage of each data source for the full set of features and for top feature types: populated places, streams, mountains, and hills. Results show wide discrepancies in coverage between the two datasets, sharp changes in feature type coverage across country borders, and idiosyncratic patterns dominated by a few countries for the more sparsely covered natural features. As more and more systems rely on recognizing and grounding named places, these patterns can influence the analysis of growing amounts of online text content and reinforce or amplify existing inequalities.

Local cultural heritage document repositories are characterized by contents strongly attached to a territory (i.e. Geographical references). The user must be able to consider such repositories according to a focus, which takes into account his/her geographical interests, and which allows one to access the relevant document's contents from a geographical point of view.

Vernacular place names are names that are commonly in use to refer to geographical places. For purposes of effective information retrieval, the spatial extent associated with these names should be able to reflect people's perception of the place, even though this may differ sometimes from the administrative definition of the same place name. Due to their informal nature, vernacular place names are hard to capture, but methods to acquire and define vernacular place names are of great benefit to search engines and all kind of information services that deal with geographic data. This paper discusses the acquisition of vernacular use of place names from web sources and their representation as surface models derived by kernel density estimators.

not only for documents containing the word castles, but also for documents which have some georeference indicating that they lie within Scotland. This in turn requires that firstly, references to locations must be identified within web documents, and secondly a footprint must be assigned to these references. This process is commonly referred to as geoparsing and geocoding (Larson, 1996). Such

Purpose -The National Archives (TNA) is the UK government's official archive. It stores and maintains records spanning over a thousand years in both physical and digital form. Much of the information held by TNA includes references to place and frequently user queries to TNA's online catalogue involve searches for location. The purpose of this paper is to illustrate how TNA have extracted the geographic references in their historic data to improve access to the archives. Approach -To be able to quickly enhance the existing archival data with geographic information, existing technologies from Natural Language Processing (NLP) and Geographical Information Retrieval (GIR) have been utilised and adapted to historical archives. Findings -Enhancing the archival records with geographic information has enabled TNA to quickly develop a number of case-studies highlighting how geographic information can improve access to large-scale archival collections. The use of existing methods from the GIR domain and technologies, such as OpenLayers, enabled us to quickly implement this process in a way that is easily transferrable to other institutions. Practical implications -The methods and technologies described in this paper can be adapted by other archives to similarly enhance access to their historic data. Also the data-sharing methods described can be used to enable the integration of knowledge held at different archival institutions. Value -Place is one of the core dimensions for TNA's archival data. Many of the records that we hold make reference to place data (wills, legislation, court cases…) and approximately one fifth of users' searches involve place names. However, there are still a number of open questions regarding the adaptation of existing GIR methods to the history domain. This paper presents an overview over available GIR methods and the challenges in applying them to historical data.

This paper evaluates scalable distributed crawling by means of the geographical partition of the Web. The approach is based on the existence of multiple distributed crawlers each one responsible for the pages belonging to one or more previously identified geographical zones. The work considers a distributed crawler where the assignment of pages to visit is based on page content geographical scope. For the initial assignment of a page to a partition we use a simple heuristic that marks a page within the same scope of the hosting web server geographical location. During download, if the analyze of a page contents recommends a different geographical scope, the page is forwarded to the well-located web server.

Several tasks related to geographical information retrieval and to the geographical information sciences involve toponym matching, that is, the problem of matching place names that share a common referent. In this article, we present the results of a wide-ranging evaluation on the performance of different string similarity metrics over the toponym matching task. We also report on experiments involving the usage of supervised machine learning for combining multiple similarity metrics, which has the natural advantage of avoiding the manual tuning of similarity thresholds. Experiments with a very large dataset show that the performance differences for the individual similarity metrics are relatively small, and that carefully tuning the similarity threshold is important for achieving good results. The methods based on supervised machine learning, particularly when considering ensembles of decision trees, can achieve good results on this task, significantly outperforming the individual similarity metrics.

The relevance of geographic information has become an emerging problem in geographic information science due to an enormous increase in volumes of data at high spatial, temporal, and semantic resolution, because of ever faster rates of new data capturing. At the same time, it is not clear whether the concept of relevance developed in information science and implemented for document-based information retrieval can be directly applied to this new, highly dynamic setting. In this study, we analyze the criteria users apply when judging the relevance of geographic entities in a given mobile usage context. Two different experiments have been set up in order to gather users' opinions on a set of possible criteria, and their relevance judgements in a given scenario. The importance ascribed to the criteria in both experiments clearly implies that a new concept of relevance is required when dealing with geographic entities instead of digital documents. This new concept of ‘Geographic Relevance’ is highly dependent on personal mobility and user's activity, whose understanding may in turn be refined by the assimilation of ‘Geographic Relevance’ itself.

Recent advances in mobile technologies led to new spatially-and context-aware definitions of relevance. In this paper, we aim to develop the conceptual framework suggested by Mizzaro (1998) further, in order to improve the characterization and classification of current and future concepts of relevance. We formalise two new dimension of relevance. The first dimension emphasizes the spatio-temporal nature of the information seeking process. The second dimension is necessary to describe how different concepts of relevance rely on different abstractions of reality.

Geographic information retrieval is a new and evolving domain. The development of GIR systems requires the analysis of requirements for such systems and, after systems are implemented their evaluation. This paper describes requirement analysis and evaluation for the SPIRIT system. Methods of user and system-centred evaluation are described and a methodology for building a document collection to facilitate derivation of

This is a thorough analysis of two techniques applied to Geographic Information Retrieval (GIR). Previous studies have researched the application of query expansion to improve the selection process of information retrieval systems. This paper emphasizes the effectiveness of the filtering of relevant documents applied to a GIR system, instead of query expansion. Based on the CLEF (Cross Language Evaluation Forum) framework available, several experiments have been run. Some based on query expansion, some on the filtering of relevant documents. The results show that filtering works better in a GIR environment, because relevant documents are not reordered in the final list.

This paper discusses evaluation of Geo-IR systems, arguing for a separate study of the different algorithmic components involved. It presents existing resources for evaluating the different components, together with a review on previous results in the area.

Local search services allow a user to search for businesses that satisfy a given geographical constraint. In contrast to traditional web search engines, current local search services rely heavily on static, structured data. Although this yields very accurate systems, it also implies a limited coverage, and limited support for using landmarks and neighborhood names in queries. To overcome these limitations,

Metonymically used location names (toponyms) refer to other, related entities and thus possess a meaning different from their literal, geographic sense. Metonymic uses are to be treated differently to improve the performance of geographic information retrieval (GIR). Statistics on toponym senses show that 75.06% of all location names are used in their literal sense, 17.05% are used metonymically, and 7.89% have a mixed sense. This article presents a method for disambiguating location names in texts between literal and metonymic senses, based on shallow features.The evaluation of this method is two‐fold. First, we use a memory‐based learner (TiMBL) to train a classifier and determine standard evaluation measures such as F‐score and accuracy. The classifier achieved an F‐score of 0.842 and an accuracy of 0.846 for identifying toponym senses in a subset of the CoNLL (Conference on Natural Language Learning) data.Second, we perform retrieval experiments based on the GeoCLEF data (newspaper article corpus and queries) from 2005 and 2006. We compare searching location names in a database index containing both their literal and metonymic senses with searching in an index containing their literal senses only. Evaluation results indicate that removing metonymic senses from the index yields a higher mean average precision (MAP) for GIR. In total, we observed a significant gain in MAP: an increase from 0.0704 to 0.0715 MAP for the GeoCLEF 2005 data, and an increase from 0.1944 to 0.2100 MAP for the GeoCLEF 2006 data.

GeoTime for the NTCIR Workshop 9 is the second evaluation of Geographic and Temporal Information Retrieval called “NTCIR GeoTime”. The focus of this task is on search with Geographic and Temporal constraints. This overview describes the data collections (Japanese and English news stories), topic development, assessment results and lessons learned from this second NTCIR GeoTime task, which combines GIR with timebased search to find specific events in a multilingual collection. Six teams submitted Japanese runs and nine teams submitted English runs. Three teams participated in both Japanese and English.

Local cultural heritage document collections are characterized by contents strongly attached to a territory and its history. Our contribution aims at enhancing such a content retrieval process efficiently each time a query includes geographic criteria. We propose a core model for a formal representation of geographic information. It takes into account the characteristics of different expression modes: written language and captures of drawings, maps, photographs, etc. We have developed a prototype fully implementing geographic information extraction (IE) and geographic information retrieval (IR) processes. We approach geographic IE from semantic processings additionally to classic IE approaches. This paper focuses on IR and information visualization (IV) proposals relying on the geospatial characteristics of documents.

This paper reports on the GikiP pilot task that took place in 2008 in GeoCLEF. This pilot task requires a combination of methods from geographical information retrieval and question answering to answer queries to the Wikipedia. We start by the task description, providing details on our topic choice and evaluation measures. Then we offer a brief motivation from several perspectives and we present results in detail. A comparison of participants' approaches is then presented, and the paper concludes with improvements for the next edition.

Geographic Information Retrieval is fast emerging as an interdisciplinary hot-topic, both in an academic and commercial sense. Retrieving data based not only on conceptual key words, but some notion of the locational relevance of the information requires research of a range of techniques, for example• the extraction of geographic terms from structured and, more challengingly, unstructured data;• the identification and removal of ambiguities in such extraction procedures;• methodologies for sffeciently storing information about locations and their relationship;• development of search engines and algorithms to take advantage of such geographic information;• the combination of geographic and contextual relevance to give a meaningful combined relevance to documents; and• techniques to allow the user to interact with and explore the results of queries to a geographically-aware IR system.

Retrieving data based not only on key words is a challenge. We worked on semi-structured data (cultural heritage corpora). Our project aimed at getting the most relevant text-units of documents (sets of sentences, paragraphs, sections, etc.) according to a spatial query. This paper proposes a method to build summarized spatial indexes for text-units based on spatial patterns. This approach adds semantic interpretation to classical indexing methods.

This paper describes our participation at GeoCLEF 2005. We detail the main software components of our Geo-IR system, its adaptation for GeoCLEF and the obtained results. The software architecture includes a geographic knowledge base, a text mining tool for geo-referencing documents, and a geo-ranking component. Results show that geo-ranking is heavily dependent on the information in the knowledge base and on the ranking algorithm involved.

Geographic Information Retrieval is concerned with retrieving documents in response to a spatially related query. This paper addresses the ranking of documents by both textual and spatial relevance. To this end, we introduce distributed ranking, where similar documents are ranked spread in the list instead of consecutively. The effect of this is that documents close together in the ranked list have less redundant information. We present various ranking methods, efficient algorithms to implement them, and experiments to show the outcome of the methods.

Gazetteers are dictionaries of geographic place-names that have important implications far beyond the worlds of geographers and cartographers. By containing ‘definitive’ lists of places, gazetteers have the ontological power to define what will and will not be geocoded and represented in databases, maps, search engines, and ultimately our spatial understandings of place. This paper focuses attention on GeoNames, which is the world's largest freely available and widely used gazetteer. We illustrate how content in GeoNames is characterised by highly uneven spatial distributions. There are dense clusters of place-names in some parts of the world and a relative absence of geographic content in others. These patterns are related not just to the wealth and population size of a country, but also to its policies on Internet access and open data. The paper then traces some of the specific implications of this information inequality: showing how biases in gazetteers are propagated in a variety of geographic meaning-making.

Metonymic location names refer to other, related entities and possess a meaning different from the literal, geographic sense. Metonymic names are to be treated differently to improve performance of geographic information retrieval (GIR). This paper presents a method for disambiguating location names in textual information to distinguish literal and metonymic senses, based on shallow features.

With the aim to improve the quality of gazetteers for geographic information retrieval systems, we present a method to detect place names employed by people submitting information to web resources. We investigate how often people refer to a place using locative phrases in web queries and address the problem of defining cognitively significant place names. We propose web mining as a means to decide whether a given particular named entity is in fact a place.

Geographic information is increasingly used in mobile contexts. Mobility constrains several aspects of this mobile usage, such as limited screen estate, number of desired interactions, or availability due to battery time. As a consequence designers and developers of mobile geographic applications strive to reduce the amount of information delivered to users and aim at serving just useful content rather than a larger amount of unspecific data. This is to address the problem of information overload as well as to provide information that is relevant. Ultimately this is the goal of any information retrieval system.
Thus, we want to set off by studying how relevance of information is defined and handled in information science/information retrieval (IR), Geographic Information Retrieval (GIR), Mobile Information Retrieval (MIR), Location Based Services (LBS), and Geographic Relevance (GR). The objective is to reveal commonalities as well as differences among these fields, mainly between GIR and GR, and eventually show potential mutual benefits.

... Hill, 1990s Range = 2 + Walker et al., 1992 Range = MIN( , ) Beard and Sharma, 1997 Case 1: Q contains C - Range = Case 2: Q and C overlap – Range = % (1− %)+100 Case 3: Q contained in C - Range = Sallaberry et al., 2006 PIV prototype (v1) - Range = + 2+ ...

We present a method that uses GeoWordNet for Geographical Information Retrieval. During the indexing phase, all places are disambiguated and assigned their coordinates on the world map. Documents are first searched for by means of a term-based search method, and then re-ranked according to the geographical information. The results show that map-based re-ranking allows to improve the results obtained by the base system, which relies only on textual information.

This paper presents an automatic annotation of spatial expressions enabling the improvement of the indexing process of non-structured geographic information. The proposed method combines the use of specific intra-sentential relationships and external resources. It relies on expanded spatial named entities recognition to deduce a symbolic representation ex- pressed in terms of semantic features, on the one hand, and, to give them a numerical representation, on the other hand. Our method completely implemented and was tested on a corpus of travelogues.