Discipline: Computer Sciences and Information Management
Subcategory: Computer Science & Information Systems
Session: 3
James Roberts - Winston-Salem State University
Co-Author(s): Dr. Debzani Deb, Winston-Salem State University, Winston-Salem, NC ; Dr. Russell Smith, Winston-Salem State University, Winston-Salem, NC
Spatial justice is a relatively new concept of social justice considered in the context of geographical space. According to Rocco [1], “Spatial Justice refers to general access to public goods, basic services, cultural goods, economic opportunity and healthy environments”. Soja [1] argues that justice has a geography and achieving spatial justice would be a means by which to address the inequitable distribution of goods, services and resources. But how is the achievement of spatial justice to be consistently assessed? We argue that there is a data-driven means for developing a spatial justice index (SJI) which would allow us to make an objective and accurate assessment of spatial justice/injustice. The spatial units we consider in this study are the geographic units known as census tracts, as defined by the US Census Bureau. The study operationalizes Rocco’s contextual explanation of spatial justice in the features such as public goods (number and proximity of parks, fire stations, water/sewer, school etc.), basic services (number and proximity of grocery stores, gas stations, business establishments etc.), cultural goods (number and proximity of libraries, museums, community centers etc.), economic opportunity (number of jobs, travel time to work, road network, poverty rate, public transport etc.), and health factors (EPA indicators, food deserts, brownfields, locally unwanted land uses, crime rate etc.). We hypothesized that the Census tracts with greater access (measured as the presence/number of a variable within the census tract) to items listed above will have higher values for SJI (i.e. lesser spatial injustice). The methodology includes 1) creating necessary data sets by downloading and cleaning the census tracts data [3] corresponding to the abovementioned features, 2) exploring features that are most correlated with spatial justice, 3) building a predictive model that can meaningfully provide insights about the SJI, and 4) comparing our model-generated SJI with other geographic goodness measures (e.g., per capita income, median household income) to validate our hypothesis. This study particularly focuses on the census tracts of Forsyth county in the US state of North Carolina while developing SJI and validating our hypothesis, with the vision that the developed SJI can be applied across the entire country to help communities comprehend, accept and potentially combat spatially unjust geographies within their communities. The results of the study are promising, showing the importance of applying the proposed data science based approach, and providing us with important insights about the SJI and its application in identifying spatial justice. 1. Rocco de Campos Pereira, “Why Discuss Spatial Justice in Urbanism Studies”, Atlantis, 24 (4), 2014. 2. Edward W. Soja “Seeking Spatial Justice”, University of Minnesota Press, 2010, ISBN: 978-0816666683 3. United States Census Bureau, https://www.census.gov
Funder Acknowledgement(s): This study is supported by NSF HBCU-UP grant #1600864 awarded to Dr. Debzani Deb, Associate Professor, Winston-Salem State University.
Faculty Advisor: Debzani Deb, debd@wssu.edu
Role: Reviewed a large amount of literature as the topic is rather contemporary, Downloaded and created the datasets, wrote python code to create the predictive models, Helped my advisor in analyzing and summarizing the results etc.