GeoExplainer: A Visual Analytics Framework for Spatial Modeling Contextualization and Report Generation.

Geographic regression models of various descriptions are often applied to identify patterns and anomalies in the determinants of spatially distributed observations. These types of analyses focus on answering why questions about underlying spatial phenomena, e.g., why is crime higher in this locale, why do children in one school district outperform those in another, etc.? Answers to these questions require explanations of the model structure, the choice of parameters, and contextualization of the findings with respect to their geographic context. This is particularly true for local forms of regression models which are focused on the role of locational context in determining human behavior. In this paper, we present GeoExplainer, a visual analytics framework designed to support analysts in creating explanative documentation that summarizes and contextualizes their spatial analyses. As analysts create their spatial models, our framework flags potential issues with model parameter selections, utilizes template-based text generation to summarize model outputs, and links with external knowledge repositories to provide annotations that help to explain the model results. As analysts explore the model results, all visualizations and annotations can be captured in an interactive report generation widget. We demonstrate our framework using a case study modeling the determinants of voting in the 2016 US Presidential Election.

A Replication of DiMaggio et al. (2020) in Phoenix, AZ.

This research replicates in Phoenix, Arizona a study originally conducted by DiMaggio et al. (2020) that investigated the associations between positive COVID-19 tests and demographic, socioeconomic, and racial characteristics in New York City at the ZIP Code Tabulation Area level. We extend that work through a conceptual replication that introduces covariates appropriate to Phoenix, AZ. Our direct replication, which focuses on that city's first wave of COVID-19 (May 31, 2020 to August 1, 2020), demonstrates that the framework used by DiMaggio et al. can be transferred across cities, but also identifies specification decisions that need careful consideration. Our conceptual replication identifies the proportion of Hispanic residents, rather than that of Black/African American residents, to be a key predictor of positive COVID-19 testing. This finding sheds light on the dynamics of race during the pandemic.