Artigos 16 de April de 2021

Visualizing the Brazilian Diaspora in the United States: A Digaai – Spark Project

This project was developed in partnership with BU SPARK!, a technology incubator and experiential learning lab for student-led computational and data-driven projects at Boston University.  As part of the CS 506 class, students Junhe Chen, Haoyu Zhang, and Hui Li, developed a platform to visualize the Brazilian population in the United States utilizing U.S. Census data. SPARK! and DIGAAI has collaborated on a series of projects focusing on the Brazilian diaspora.

The project’s main goal was to visualize the Brazilian population in the United States by understanding how Brazilians cluster in each state based on location and population size. The visualization involved the study and the creation of a visual representation of the data, meaning ” information that has been abstracted in some schematic form, including attributes or variables for the units of information.”The team analyzed the different attributes in the data set of the distribution of Brazilians in different states and tried to extract the best representative tag or feature about Brazilians in an area. The tags were normalized and vectorized in order to perform a hierarchical clustering algorithm so that users could zoom in on the map to show more detailed information in the corresponding region.

A primary goal of data visualization was to communicate information clearly and efficiently via statistical graphics, plots, and information graphics. Numerical data was encoded using dots, lines, or bars, to communicate a quantitative message visually. Effective visualization helps users analyze and reason about data and evidence. It makes complex data more accessible, understandable, and useable.

Users may have particular analytical tasks, such as making comparisons or understanding causality and the design principle of the graphic followed these tasks. Tables were generally used where users will look up a specific measurement. In contrast, charts of various types show patterns or relationships in the data for one or more variables.

A frontend was designed so that the data could be displayed on a map and plotted on charts so that attributes could then be shown as the user moves the cursor of the mouse onto the area of a state in the browser. Following is an example of what it looks like when the attribute of the group “Age Distribution” is shown as illustrated here.

A final poster of the project is available here: CS_506_Final_Poster. A complete description of the project and its methodology can be founded here: CS_506_Final_Report. And, the final visualization can be accessed by clicking on the logo “VISUALIZING THE BRAZILIAN DIASPORA” on the land page of the digaai site. To access the visualization from here, click on the logo below: