29 September 2020 in EPJ Data Science
Evacuations are a common practice to mitigate the potential risks and damages made by natural disasters. However, without proper coordination and management, evacuations can be inefficient and cause negative impact. Local governments and organizations need to have a better understanding of how the population responds to disasters and evacuation recommendations so as to enhance their disaster management processes. Previous studies mostly examine responses to evacuations at the individual or household level by using survey methods. However, population flows during disasters are not just the aggregation of individuals’ decisions, but a result of complex interactions with other individuals and the environment. We propose a method to model evacuation flows and reveal the patterns of evacuation flows at different spatial scales. Specifically, we gathered large-scale geotagged tweets during Hurricane Irma to conduct an empirical study. First, we present a method to characterize evacuation flows at different geographic scales: the state level, considering evacuation flows across southern states affected by Irma; the urban/rural area level, and the county level. Then we demonstrate results on the predictability of evacuation flows in the most affected state, Florida, by using the following environmental factors: the destructive force of the hurricane, the socioeconomic context, and the evacuation policy issued for counties. Feature analyses show that distance is a dominant predictive factor with counties that are geographically closer generally having larger evacuation flows. Socioeconomic levels are positively related to evacuation flows, with popular destinations associated to higher socioeconomic levels. The results presented in this paper can help decision makers to better understand population evacuation behaviors given certain environmental features, which in turn will aid in the design of efficient and informed preparedness and response strategies.
8 November 2022 in EPJ Data Science
Place-based short-term crime prediction models leverage the spatio-temporal patterns of historical crimes to predict aggregate volumes of crime incidents at specific locations over time. Under the umbrella of the crime opportunity theory, that suggests that human mobility can play a role in crime generation, increasing attention has been paid to the predictive power of human mobility in place-based short-term crime models. Researchers have used call detail records (CDR), data from location-based services such as Foursquare or from social media to characterize human mobility; and have shown that mobility metrics, together with historical crime data, can improve short-term crime prediction accuracy. In this paper, we propose to use a publicly available fine-grained human mobility dataset from a location intelligence company to explore the effects of human mobility features on short-term crime prediction. For that purpose, we conduct a comprehensive evaluation across multiple cities with diverse demographic characteristics, different types of crimes and various deep learning models; and we show that adding human mobility flow features to historical crimes can improve the F1 scores for a variety of neural crime prediction models across cities and types of crimes, with improvements ranging from 2% to 7%. Our analysis also shows that some neural architectures can slightly improve the crime prediction performance when compared to non-neural regression models by at most 2%.
1 November 2021 in Transportation Research Part D: Transport and Environment
5 July 2022 in JMIR Public Health and Surveillance
Background: The issue of food insecurity is becoming increasingly important to public health practitioners because of the adverse health outcomes and underlying racial disparities associated with insufficient access to healthy foods. Prior research has used data sources such as surveys, geographic information systems, and food store assessments to identify regions classified as food deserts but perhaps the individuals in these regions unknowingly provide their own accounts of food consumption and food insecurity through social media. Social media data have proved useful in answering questions related to public health; therefore, these data are a rich source for identifying food deserts in the United States.Objective: The aim of this study was to develop, from geotagged Twitter data, a predictive model for the identification of food deserts in the United States using the linguistic constructs found in food-related tweets.Methods: Twitter’s streaming application programming interface was used to collect a random 1% sample of public geolocated tweets across 25 major cities from March 2020 to December 2020. A total of 60,174 geolocated food-related tweets were collected across the 25 cities. Each geolocated tweet was mapped to its respective census tract using point-to-polygon mapping, which allowed us to develop census tract–level features derived from the linguistic constructs found in food-related tweets, such as tweet sentiment and average nutritional value of foods mentioned in the tweets. These features were then used to examine the associations between food desert status and the food ingestion language and sentiment of tweets in a census tract and to determine whether food-related tweets can be used to infer census tract–level food desert status.Results: We found associations between a census tract being classified as a food desert and an increase in the number of tweets in a census tract that mentioned unhealthy foods (P=.03), including foods high in cholesterol (P=.02) or low in key nutrients such as potassium (P=.01). We also found an association between a census tract being classified as a food desert and an increase in the proportion of tweets that mentioned healthy foods (P=.03) and fast-food restaurants (P=.01) with positive sentiment. In addition, we found that including food ingestion language derived from tweets in classification models that predict food desert status improves model performance compared with baseline models that only include socioeconomic characteristics.Conclusions: Social media data have been increasingly used to answer questions related to health and well-being. Using Twitter data, we found that food-related tweets can be used to develop models for predicting census tract food desert status with high accuracy and improve over baseline models. Food ingestion language found in tweets, such as census tract–level measures of food sentiment and healthiness, are associated with census tract–level food desert status.
29 October 2019 in Environment and Planning B: Urban Analytics and City Science
The field of urban analytics and city science has seen significant growth and development in the past 20 years. The rise of data science, both in industry and academia, has put new pressures on urban research, but has also allowed for new analytical possibilities. Because of the rapid growth and change in the field, terminology in urban analytics can be vague and unclear. This paper, an abridged synthesis of a panel discussion among scholars in Urban Data Science held at the 2019 American Association of Geographers Conference in Washington, D.C., outlines one discussion seeking a better sense of the conceptual, terminological, social, and ethical challenges faced by researchers in this emergent field. The panel outlines the difficulties of defining what is or is not urban data science, finding that good urban data science must have an expansive role in a successful discipline of “city science.” It suggests that “data science” has value as a “signaling” term in industrial or popular science applications, but which may not necessarily be well-understood within purely academic circles. The panel also discusses the normative value of doing urban data science, linking successful practice back to urban life. Overall, this panel report contributes to the wider discussion around urban analytics and city science and about the role of data science in this domain.