In this commentary, we describe the current state of the art of points of interest (POIs) as digital, spatial datasets, both in terms of their quality and affordings, and how they are used across research domains. We argue that good spatial coverage and high-quality POI features — especially POI category and temporality information — are key for creating reliable data. We list challenges in POI geolocation and spatial representation, data fidelity, and POI attributes, and address how these challenges may affect the results of geospatial analyses of the built environment for applications in public health, urban planning, sustainable development, mobility, community studies, and sociology. This commentary is intended to shed more light on the importance of POIs both as standalone spatial datasets and as input to geospatial analyses.
21 February 2018 in Foundations and Trends® in Information Retrieval
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.
12 March 2019 in Journal of the Association for Information Science and Technology
Human spatial concepts, such as the concept of place, are not immediately translatable to the geometric foundations of spatial databases and information systems developed over the past 50 years. These systems typically rest on the concepts of objects and fields, both bound to coordinates, as two general paradigms of geographic representation. The match between notions of place occurring in everyday where questions and the data available to answer such questions is unclear and hinders progress in place‐based information systems. This is particularly true in novel application areas such as the Digital Humanities or speech‐based human–computer interaction, but also for location‐based services. Although this shortcoming has been observed before, we approach the challenges of relating places to information system representations with a fresh view, based on a set of core concepts of spatial information. These concepts have been proposed in information science with the intent of serving human–machine spatial question asking and answering. Clarifying the relationship of the notion of place to these concepts is a significant step toward geographically intelligent systems. The main result of the article is a demonstration that the notion of place fits existing concepts of spatial information, when these are adequately exploited and combined.
Participatory mapping of local land use as the basis for planning and decision-making has become widespread around the globe. However, still relatively little is known about the conceptual underpinnings of geographic information produced through participatory mapping in given cultural and linguistic settings. In this paper, we therefore address the seemingly simple question of what is (not) represented on maps through an exploratory case study comparing land use categories participants represented on sketch maps with categories elicited through more language-focused ethnographic fieldwork. To explore landscape categorization, we conducted sketch mapping with 29 participants and in-depth ethnographic fieldwork with 19 participants from the Takana indigenous people in the Bolivian Amazon. Sketch mapping resulted in 74 different feature types, while we elicited 156 landscape categories used in language, of which only 23 overlapped with feature types from the sketch mapping. Vegetation categories were highly diversified in language but seldom represented on maps, while more obviously anthropogenic features were represented on sketch maps. Furthermore, participants seldom drew culturally important landscape categories such as fallow plots or important plant harvesting sites on maps, with important potential consequences for natural resource management.
26 November 2019 in IEEE Transactions on Intelligent Transportation Systems
Detecting traffic events and their locations is important for an effective transportation management system and better urban policy making. Traffic events are related to traffic accidents, congestion, parking issues, to name a few. Currently, traffic events are detected through static sensors e.g., CCTV camera, loop detectors. However they have limited spatial coverage and high maintenance cost, especially in developing regions. On the other hand, with Web 2.0 and ubiquitous mobile platforms, people can act as social sensors sharing different traffic events along with their locations. We investigated whether Twitter - a social media platform can be useful to understand urban traffic events from tweets in India. However, such tweets are informal and noisy and containing vernacular geographical information making the location retrieval task challenging. So far most authors have used geotagged tweets to identify traffic events which accounted for only 0.1%-3% or sometimes less than that. Recently Twitter has removed precise geotagging, further decreasing the utility of such approaches. To address these issues, this research explored how ungeotagged tweets could be used to understand traffic events in India. We developed a novel framework that does not only categorize traffic related tweets but also extracts the locations of the traffic events from the tweet content in Greater Mumbai. The results show that an SVM based model performs best detecting traffic related tweets. While extracting location information, a hybrid georeferencing model consists of a supervised learning algorithm and a number of spatial rules outperforms other models. The results suggest people in India, especially in Greater Mumbai often share traffic information along with location mentions, which can be used to complement existing physical transport infrastructure in a cost-effective manner to manage transport services in the urban environment.
9 March 2016 in Journal of the Association for Information Science and Technology
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.