Geography GIS and Computational Social Sciences
by
Xinyue Ye
  • LAST REVIEWED: 21 February 2023
  • LAST MODIFIED: 21 February 2023
  • DOI: 10.1093/obo/9780199874002-0256

Introduction

A restless intellectual dynamic has been witnessed in the field of data-driven social science in the past two decades, especially where computational social science meets GIS (geographic information science). Emerging theoretical viewpoints, data sources, and methodological advances have offered novel venues to examine both spatial and semantic information in high-dimensional and heterogeneous social datasets. Space and place can integrate social science disciplines both theoretically and methodologically. A recent surge of interests in computational social science research has been witnessed due to the increasingly availability of fine-scale human behavior and social network data. GIS-based computational social science thus emphasizes the spatio-temporal social relationships and movements ranging from micro- (individual) to macro- (social group or administrative unit) perspectives. This entry opens with GIS and Computational Social Science: History and Status and the frameworks on which it is based. We have identified three interrelated themes and one trend: (1) Spatial Regression and Simulation, (2) Spatial Social Networking, (3) Human Mobility, and (4) integrated conceptualizations, analytical methods, and open source packages toward synthesis and convergence. The convergence between GIS and Computational Social Science can be achieved through these human-centered and context-based interrelated themes. With the increasingly available detailed individual-level data and analytical tools, the cross-fertilisationbetween GIS and computational social science brings the human factor to the former while situating the latter in the spatial context. Finally, the implications of such trends in terms of achieving convergence and synthesis between GIS and computational social science are presented.

GIS and Computational Social Science: History and Status

Linking the spatial and social spaces lies at the heart of quantitative and spatial social science. Goodchild, et al. 2000 states that space and place integrate social science disciplines both theoretically and methodologically. The Center for Spatially Integrated Social Science was funded in 1999 by the National Science Foundation under its program to stimulate research infrastructure throughout the social and behavioral sciences. It aims to implement and provide packages (such as GeoDa) and best practices that will enhance the spatial analytic capabilities of researchers across the social sciences. As a popular term, spatially integrated social science has been used and investigated by researchers and organizations in various fields from very diverse angles, with particular attention to location, spatial structure, and spatial processes. Advancements in location-aware technology, information and communication technology, and mobile technology during the past two decades have transformed the focus and need for urban research from mostly static assessments to multi-scalar assessments that span spatial, temporal, and dynamic relationships and integrate human behaviors across various environments (natural, built, and virtual). Lazer, et al. 2009 further notes that the human behaviors and interactions have been unprecedentedly observed and recorded at fine spatial, temporal, and digital resolutions in both virtual and physical worlds, rendering the opportunity for computable social and behavioral dynamics. Kitts, et al. 2020 claims that computational social science flourishes at the intersection of social science and computational science, redirecting attention from structural patterns to social processes. Batty 2013 suggests developing and implementing spatiotemporal and network methods to better understand inequality, mobility, and diffusion in our social systems composed of flows and networks. Shaw, et al. 2016 offers thoughts on human-centered GIS. Ye and Liu 2018 promotes computational social science in an urban setting from the spatial perspective, while Ye and Andris 2021 presents the research framework for social network analytics within the context of geospatial big data deluge. Despite all the substantial growth in the field of computational social science, Lazer, et al. 2020 points out that the institutional structures such as research ethics, pedagogy, and data infrastructure still need to be strengthened.

  • Adams, J., K. Faust, and G. S. Lovasi, eds. “Capturing Context: Integrating Spatial and Social Network Analyses.” In Special Issue: Capturing Context: Integrating Spatial and Social Network Analyses. Social Networks 34.1 (2012): 1–5.

    DOI: 10.1016/j.socnet.2011.10.007Save Citation »Export Citation » Share Citation »

    Serves as an editorial to a special issue on integration of network and spatial analytic strategies.

    Find this resource:

  • Batty, M. The New Science of Cities. Cambridge, MA: MIT Press, 2013.

    DOI: 10.7551/mitpress/9399.001.0001Save Citation »Export Citation » Share Citation »

    Proposes a bottom-up way of understanding cities and their design not as artifacts but as systems composed of flows and networks, which is a metaphor of social network and relationships.

    Find this resource:

  • Goodchild, M. F., L. Anselin, R. P. Appelbaum, and B. H. Harthorn. “Toward Spatially Integrated Social Science.” International Regional Science Review 23.2 (2000): 139–159.

    DOI: 10.1177/016001700761012701Save Citation »Export Citation » Share Citation »

    Recognizes the mounting importance of space, spatiality, location, and place in social science studies through the vision of research community building.

    Find this resource:

  • Kitts, J. A., E. Quintane, and E. S. M. T. Berlin. “Rethinking Social Networks in the Era of Computational Social Science.” In The Oxford Handbook of Social Network Analysis. Edited by Ryan Light, and James Moody, 71–97. Oxford: Oxford University Press, 2020.

    Save Citation »Export Citation » Share Citation »

    Integrates social network analysis and computational social science from structural patterns to social processes.

    Find this resource:

  • Lazer, D., A. S. Pentland, L. Adamic, et al. “Life in the Network: The Coming Age of Computational Social Science.” Science 323.5915 (2009): 721–723.

    DOI: 10.1126/science.1167742Save Citation »Export Citation » Share Citation »

    Discusses both potential opportunities and barriers to the emergence of a computational social science.

    Find this resource:

  • Lazer, D. M., A. Pentland, D. J. Watts, et al. “Computational Social Science: Obstacles and Opportunities.” Science 369.6507 (2020): 1060–1062.

    DOI: 10.1126/science.aaz8170Save Citation »Export Citation » Share Citation »

    Suggest opportunities to facilitate the alignment between the organization of the 20th-century university and the intellectual requirements of computational social science.

    Find this resource:

  • Shaw, S- L., M- H. Tsou, and X. Ye, eds. “Editorial.” In Special Issue: Human Dynamics in the Mobile and Big Data Era. International Journal of Geographical Information Science 30.9 (2016): 1687–1693.

    DOI: 10.1080/13658816.2016.1164317Save Citation »Export Citation » Share Citation »

    Sevres as an editorial to a special issue on human dynamics, an emerging topic in human-centered GIS.

    Find this resource:

  • Tsou, M- H. “Research Challenges and Opportunities in Mapping Social Media and Big Data.” Cartography and Geographic Information Science 42.supp. 1 (2015): 70–74.

    DOI: 10.1080/15230406.2015.1059251Save Citation »Export Citation » Share Citation »

    Addresses important research challenges and major opportunities for cartographers to process and visualize big social data.

    Find this resource:

  • Ye, X. “Spatial Econometrics.” In The International Encyclopedia of Geography. Edited by Douglas Richardson, Noel Castree, Michael F. Goodchild, Audrey Kobayashi, Weidong Liu, and Richard A. Marston, 6644–6654. Chichester, UK: John Wiley and Sons, 2017.

    Save Citation »Export Citation » Share Citation »

    Reviews the theoretical thoughts, applications, and software development in spatial econometrics, especially highlighting the spatiotemporally integrated social science.

    Find this resource:

  • Ye, X., and X. Liu. “Editorial.” In Special Issue: Integrating Social Network and Spatial Analyses of the Built Environment. Environment and Planning B 45.3 (2018).

    DOI: 10.1177/2399808318772381Save Citation »Export Citation » Share Citation »

    Serves as an editorial to a special issue on spatial social network analytics in the urban setting, an emerging topic in computational social science from the spatial perspective.

    Find this resource:

  • Ye, X., and C. Andris. “Editorial.” In Special Issue: Spatial Social Networks in Geographic Information Science. International Journal of Geographical Information Science 35.12 (2021): 1–5.

    DOI: 10.1080/13658816.2021.2001722Save Citation »Export Citation » Share Citation »

    Serves as an editorial to a special issue on social network analytics in the GIS context, driven by novel conceptualizations, unprecedented data sources, AI-driven network science methods, and open-source toolbox environments.

    Find this resource:

Spatial Regression and Simulation

Spatial effects, widely recognized as fundamental drivers of many socioeconomic phenomena, refer to spatial dependence and spatial heterogeneity. Spatial dependence shows the degree of spatial autocorrelation between independently measured values. Spatial heterogeneity deals with the unequal distribution of relationships across space. Anselin 1988 notes that spatial econometrics models compute the spillover effects across spatial units to denote how any individual or collective decisions might rely on the decisions made in the neighboring geographical observations. The neighboring structure is defined by the spatial weight matrix, which depicts the interaction and association between geographical observations. Casetti 1972 formulates the expansion method to model spatial nonstationarity. Fotheringham, et al. 2003 develops Geographically Weighted Regression (GWR) taking into accounts spatial nonstationarity to derive local parameters for any locations in the study region. With the increasing availability of georeferenced point data or spatial units over time, Elhorst 2017 adopts panel data structures jointly controlling spatial and time specific effects. Spatial panel regression models contain the pooled ordinary least-squares model, the fixed-effects model, the random-effects model, and random-parameters model. Huang, et al. 2010 extends GWR to the space-time context. The synergies between applied economics and GIS also considerably improve the way in which people conceptualize and implement spatial regression tools and packages. Anselin and Rey 2012 state that open source spatial econometrics tool development has promoted interdisciplinary collaboration across social sciences. The replicable and reproducible mechanism with the computing power would significantly change the nature of spatial econometrics research. Compared to the top-down perspective of spatial regression, Batty 2007 argues that spatial simulation is bottom-up complex systems thinking and a more popular approach for computational social science. Spatial simulation is divided into two categories: CA (Cellular Automata) and ABM (Agent-Based Model). CA is based on fixed spatial neighborhoods only interacting locally with their immediate neighbors, while autonomous agents with social ability in ABM can move across space to interact with each other and other neighborhoods. Spatial simulation can take the beginners beyond the basic understanding of descriptive spatial analysis tools, which cannot model or predict systems that show surprising and unanticipated behaviors and outcomes. In addition, regression and spatial statistics can also serve as methods for the analysis and evaluation of simulation models. The importance of spatiotemporally explicit simulation to many socioeconomic theories has been gaining growing attentions and recognition.

  • Anselin, Luc. Spatial Econometrics: Methods and Models. Dordrecht, The Netherlands: Kluwer Academic Publishers, 1988.

    DOI: 10.1007/978-94-015-7799-1Save Citation »Export Citation » Share Citation »

    The first book formally establishing the theoretical and methodological framework of spatial econometrics, where spatial regression is the core.

    Find this resource:

  • Anselin, Luc. “Thirty Years of Spatial Econometrics.” Papers in Regional Science 89.1 (2010): 3–25.

    DOI: 10.1111/j.1435-5957.2010.00279.xSave Citation »Export Citation » Share Citation »

    Reviews the development of the field of spatial econometrics, arguing that it has moved from the margins to the mainstream of applied econometrics and social science methodology.

    Find this resource:

  • Anselin, L., and S. J. Rey. “Spatial Econometrics in an Age of CyberGIScience.” In Special Issue: Reflections on Geographic Information Science: Special Issue in Honor of Michael Goodchild. Edited by Nina S. Lam and Karen K. Kemp. International Journal of Geographical Information Science 26.12 (2012): 2211–2226.

    DOI: 10.1080/13658816.2012.664276Save Citation »Export Citation » Share Citation »

    Discusses the requirements and challenges encountered when moving spatial regression software tools into a CyberGIScience framework.

    Find this resource:

  • Batty, M. Cities and Complexity: Understanding Cities with Cellular Automata, Agent-based Models, and Fractals. Cambridge, MA: The MIT Press, 2007.

    Save Citation »Export Citation » Share Citation »

    Demonstrates how cities can be simulated in terms of cells and agents.

    Find this resource:

  • Casetti, E. “Generating Models by the Expansion Method: Applications to Geographical Research.” Geographical Analysis 4.1 (1972): 81–91.

    DOI: 10.1111/j.1538-4632.1972.tb00458.xSave Citation »Export Citation » Share Citation »

    One of the earliest articles on measuring and incorporating spatial nonstationarity. The geographically weighted regression is considered as a natural evolution of the expansion method.

    Find this resource:

  • Elhorst, J. P. “Spatial Panel Data Analysis.” Encyclopedia of GIS 2 (2017): 2050–2058.

    DOI: 10.1007/978-3-319-17885-1_1641Save Citation »Export Citation » Share Citation »

    A compressive overview of spatial pane regression and the codes and tools involved.

    Find this resource:

  • Fotheringham, A. S., C. Brunsdon, and M. Charlton. Geographically Weighted Regression: The Analysis of Spatially Varying Relationships. Chichester, UK: John Wiley & Sons, 2003.

    Save Citation »Export Citation » Share Citation »

    The first and only book on geographically weighted regression.

    Find this resource:

  • Huang, B., B. Wu, and M. Barry. “Geographically and Temporally Weighted Regression for Modeling Spatio-temporal Variation in House Prices.” International Journal of Geographical Information Science 24.3 (2010): 383–401.

    DOI: 10.1080/13658810802672469Save Citation »Export Citation » Share Citation »

    Adds the time effect to GWR (geographically weighted regression) model.

    Find this resource:

  • O’Sullivan, D., and G. L. Perry. Spatial Simulation: Exploring Pattern and Process. Hoboken, NJ: John Wiley & Sons, 2013.

    DOI: 10.1002/9781118527085Save Citation »Export Citation » Share Citation »

    Brings a comprehensiveness and structure to the field of spatial simulation using open source tools.

    Find this resource:

  • Paelinck, J. H. P., and L. H. Klaassen. Spatial Econometrics. Farnborough, UK: Saxon House, 1979.

    Save Citation »Export Citation » Share Citation »

    The first comprehensive attempt to set the stage for spatial econometrics, where spatial analysis and econometrics intersect.

    Find this resource:

  • Song, Y., J. Wang, Y. Ge, and C. Xu. “An Optimal Parameters-based Geographical Detector Model Enhances Geographic Characteristics of Explanatory Variables for Spatial Heterogeneity Analysis: Cases with Different Types of Spatial Data.” GIScience & Remote Sensing 57 (2020): 1–17.

    DOI: 10.1080/15481603.2020.1760434Save Citation »Export Citation » Share Citation »

    Deals with spatial data discretization and spatial scale effects for more accurate spatial stratified heterogeneity analysis.

    Find this resource:

Spatial Social Networking

Milgram 1967 argues that society is formed by many interrelated contexts where agents interact with each other over social networks, such as six degrees of separation. Andris 2016 notes that there is an intertwined system composed of geographic landscapes and social networks that simultaneously configure our social life. Additionally, spatial social networking concerns big and mobile human dynamics in a hybrid physical-virtual environment, because people can be connected to each other through cyberspace, telecommunication space, and social space in many physical spaces. These activities and interactions taking place in virtual space influence and interact with those in physical geographic space, thus rendering spatial social networks as embedded simultaneously in physical and relational spaces. Emphasizing spatiality of social networks, Zenou 2013 argues that the difficulty of spatial access to weak social ties broadens the inequality of job seeking. The notion of spatial social networks can help break down disciplinary silos and stimulate convergence research, harnessing social complexity. Many GIS methods have been generated to deal with high-dimensional, heterogeneous, and unstructured social network data. Firestone, et al. 2011 depicts the space-time dynamics of early epidemic spread incorporating the clustering of infected cases with contact network topology, highlighting the importance of both geographic location and contact network position. Kim, et al. 2020 proposes a framework to identify influential agents in social networks and geographic space in relation to travel mode choice by estimating social distance based on similar activity-travel decisions and identifying the spatial and activity-travel characteristics of the influential agents. Sarkar, et al. 2019 develops the spatial social network schema, tuning parameters, and flattening ratio to answer the questions such as locating key agents responsible for maintaining the social network at various spatial scales and levels. Hence, geographic distance, proximity, and structure will shape social networks in the interrelated contexts over time. As Shaw and Sui 2018 has pointed out, people tend to become more spontaneous in arranging activities, which enriches more opportunities to gain insights from human dynamics data. The boosting of the need to handle spatial social networking significantly challenges a GIS research community traditionally built on absolute space.

  • Andris, C. “Integrating Social Network Data into GISystems.” International Journal of Geographical Information Science 30.10 (2016): 2009–2031.

    Save Citation »Export Citation » Share Citation »

    Facilitates a framework for analyzing social network within geographic space by combining the mature fields of social network analysis and GISystems.

    Find this resource:

  • Barabási, A.- L. “The Origin of Bursts and Heavy Tails in Human Dynamics.” Nature 435.7039 (2005): 207–211.

    DOI: 10.1038/nature03459Save Citation »Export Citation » Share Citation »

    Shows that the burst-oriented nature of human behavior is a consequence of a decision-based queuing process.

    Find this resource:

  • Firestone, S. M., M. P. Ward, R. M. Christley, and N. K. Dhand. “The Importance of Location in Contact Networks: Describing Early Epidemic Spread Using Spatial Social Network Analysis.” Preventive Veterinary Medicine 102.3 (2011): 185–195.

    DOI: 10.1016/j.prevetmed.2011.07.006Save Citation »Export Citation » Share Citation »

    Explores methods for describing the dynamics of early epidemic spread and the clustering of infected cases in space and time when an underlying contact network structure is influencing disease spread.

    Find this resource:

  • Granovetter, M. S. “The Strength of Weak Ties.” American Journal of Sociology 78.6 (May 1973): 1360–1380.

    DOI: 10.1086/225469Save Citation »Export Citation » Share Citation »

    Emphasizes the analysis of segments of social structure not easily defined in terms of primary groups.

    Find this resource:

  • Hillier, B., and J. Hanson. The Social Logic of Space. Cambridge, UK: Cambridge University Press, 1984.

    DOI: 10.1017/CBO9780511597237Save Citation »Export Citation » Share Citation »

    Theorizes and examines what it is about different types of societies that leads them to adopt different spatial forms.

    Find this resource:

  • Kim, J., Y. K. Bae, and J.- H. Chung. “Modeling Social Distance and Activity-travel Decision Similarity to Identify Influential Agents in Social Networks and Geographic Space and Its Application to Travel Mode Choice Analysis.” Transportation Research Record 2674.6 (2020): 0361198120919412.

    DOI: 10.1177/0361198120919412Save Citation »Export Citation » Share Citation »

    Addresses conformity behavior in activity-travel decisions, implying that in making such decisions people mimic the behavior of other members of their social networks.

    Find this resource:

  • Sarkar, D., C. Andris, C. A. Chapman, and R. Sengupta. “Metrics for Characterizing Network Structure and Node Importance in Spatial Social Networks.” International Journal of Geographical Information Science 33.5 (2019): 1017–1039.

    DOI: 10.1080/13658816.2019.1567736Save Citation »Export Citation » Share Citation »

    Introduces a set of new metrics focusing on the notion of ‘distance’ for spatial social network analysis.

    Find this resource:

  • Milgram, S. “The Small World Problem.” Psychology Today 2 (1967): 60–67.

    Save Citation »Export Citation » Share Citation »

    Conducted a seminal experiment to test the hypothesis that scattered members of any large social network could be connected to each other through short chains of intermediate acquaintances.

    Find this resource:

  • Ye, X., and X. Liu, eds. Cities as Social and Spatial Networks. New York: Springer, 2019.

    Save Citation »Export Citation » Share Citation »

    Reports the methods and practice on integrating social network and spatial analyses in the built environment.

    Find this resource:

  • Zenou, Y. “Spatial versus Social Mismatch.” Journal of Urban Economics 74 (2013): 113–132.

    DOI: 10.1016/j.jue.2012.11.002Save Citation »Export Citation » Share Citation »

    Provides a spatial mechanism on social interactions, explaining why distance to jobs can have a negative impact on workers’ labor-market outcomes, especially ethnic minorities.

    Find this resource:

Human Mobility

With modern sensor and location-aware technologies, vendors, service providers, and government agencies have collected large amounts of tracking data on a wide range of human movements at a high spatial and temporal granularity and at affordable costs. Miller 1991 modeled human behavior through a space-time prism by integrating the space-time of time-geographical frameworks and geographic information systems. The space-time prism concept has been further developed in Yu and Shaw 2008 to represent, visualize, and analyze potential human activities and interactions in physical and virtual spaces. Because the tracking data and computing power can be accessed at low or even no cost recently, time geography has gained more attention in computational social science research. Geovisualization methods reveal the multifaceted interaction of human spatial behavior and guide it toward human behavioral models formulation. In addition, more exploratory visualization systems are needed to study trajectories with efficient user interaction and instant visual feedback through an iterative information search-and-reasoning approach. Via effective big data management and visual analytics platforms, nonexpert users focus more on the research questions instead of worrying about the lack of software packages and computing resources. Shamal, et al. 2019 implements TrajAnalytics both as a standalone and cloud-based open source package of interactively visualizing traffic flow data which can be used by common users over their own computers or mobile devices. With scalable data storage and management immediately supporting a variety of data queries, TrajAnalytics intuitively guides nonexpert users through the whole procedure of mobility visual analytics on an easy access gateway, starting by uploading raw trajectory data organized as commonly as a csv file, relieving the domain users from the burden of big data administration and computing power. As a multiuser system, TrajAnalytics allows simultaneous operations by many users from different places.

Integration, Synthesis, and Convergence

To situate and contextualize computational social science in both physical and virtual spaces, the effective and efficient representation and management of spatial social data has proliferated rapidly across computational social science research. To gain insights into human activities and interactions is essential to facilitate such integration, synthesis, and convergence during our mobile and big data era. The network and flow view of the world offers a powerful repertoire of tools, techniques, and metaphors. The collaborative component of social modeling is vital to glue the efforts of researchers and agencies. Their results should be sharable and leveraged by others. Although the mainstream GIS operation allows users to identify the changes between snapshots, it cannot effectively and efficiently represent, model, and visualize events and processes involving multiple spatiotemporal dynamics in the real world. Shaw and Sui 2020 suggest the existence of notions of relative space and relational space to detect relative locations and topological relationships. The integration of GIS and Computational Social Science would facilitate integration across disciplines while also addressing specific and compelling problems in certain social science domains, breaking down disciplinary silos and stimulating convergence research. To what extent the integration of GIS and computational social science can be maximized will depend on research progress in several areas. First, new social science theories need to be developed to respond to the new data and computing environment. Second, we need to understand the pros and cons of big data and traditional data in various social science disciplines before using these datasets or conduct data fusion for policymaking. We also need to deal with the data privacy and security issues. Third, novel computational methods such as geospatial artificial intelligence, natural language processing, and computer vision need to be introduced to such integration, because the current GIS and quantitative social science methods are still limited in handling the complicated big spatial data. The impact of the open source movement and large scale computing on the current GIS and computational social science is growing. Fourth, the notion of fairness in such integration should be noted. For example, it is more likely that affluent communities are overrepresented in big social data, compared to poor neighborhoods. The model based on such data distribution is likely to be biased toward the rich communities. Finally, researchers have attempted to move from understanding various kinds of spatiotemporal social dynamics to actively intervening and even designing future changes of society.

  • Schwab, K. The Fourth Industrial Revolution. Geneva, Switzerland: World Economic Forum, 2016.

    Save Citation »Export Citation » Share Citation »

    Isolates this transformation as the theme of the World Economic Forum’s 2016 Annual Meeting, for which this book serves as background reading.

    Find this resource:

  • Shaw, S.- L., and D. Sui. “GIScience for Human Dynamics Research in a Changing World.” Transactions in GIS 22.4 (2018): 891–899.

    DOI: 10.1111/tgis.12474Save Citation »Export Citation » Share Citation »

    This editorial discusses a need for GIScience to evolve to better support human dynamics research, which in turn can help GIScience gain recognition from convergence science in human dynamics research.

    Find this resource:

  • Shaw, S. L., and D. Sui. “Understanding the New Human Dynamics in Smart Spaces and Places: Toward a Splatial framework.” Annals of the American Association of Geographers 110.2 (2020): 339–348.

    DOI: 10.1080/24694452.2019.1631145Save Citation »Export Citation » Share Citation »

    Critically examines the concepts of space and place in geography in general and in geographic information science in particular so that intelligent geographic information systems incorporating concepts of smart space and smart place can be developed to support human dynamics research.

    Find this resource:

  • Sui, D. Z., and M. F. Goodchild. “GIS as Media?” International Journal of Geographical Information Science 15.5 (2001): 387–390.

    DOI: 10.1080/13658810110038924Save Citation »Export Citation » Share Citation »

    An editorial stating that geographic information systems are rapidly becoming part of the mass media, as modifiable perceptive extensions of human thought.

    Find this resource:

  • Ye, X., and H. Lin, eds. Spatial Synthesis: Computational Social Science and Humanities. Cham, Switzerland: Springer, 2020.

    Save Citation »Export Citation » Share Citation »

    Describes how powerful convergence science, computing technology, emerging big and open data sources, and theoretical perspectives on spatial synthesis have revolutionized the way in which we investigate social sciences and humanities.

    Find this resource:

  • Zhang, F., M. Hu, W. Che, H. Lin, and C. Fang. “Framework for Virtual Cognitive Experiment in Virtual Geographic Environments.” ISPRS International Journal of Geo-Information 7.1 (2018): 36.

    DOI: 10.3390/ijgi7010036Save Citation »Export Citation » Share Citation »

    Discusses the outlook of virtual geographic environments and proposes a framework for virtual cognitive experiments.

    Find this resource:

back to top

Article

Up

Down