SIBGRAPI 22 - VSG Workshop

Visualization for Social Good

We are happy to invite you to contribute to the 1st Workshop on Visualization for Social Good (VSG). VSG 2022 will be held as part of SIBGRAPI 2022 in Natal, Rio Grande do Norte, Brazil, October 24-28, 2022.

VSG is a forum for recent visualization solutions in the societal context, such as urban and sports analytics, societal and governmental data analysis, and social science in general. We welcome contributions as Short Papers, but also work previously published for presentation only. All contributions must be in English, and the proceedings will be published in the SBC Open Library.

Important Dates

• Sep 25, 2022: submission of Short Papers and previous work presentation
• Sep 29, 2022: author notification
• Oct 27, 2022: VSG workshop

Submission Guidelines

• Short Papers must not exceed 4 pages, with an additional page including only references. The LaTeX template can be found here.

• For the presentation of previously published work, a document has to be submitted including title, authors, and abstract, accompanied by the previously published document, as a single PDF file.

Contributions must be submitted via EasyChair.

For additional information, please contact us via vsgsibgrapi22@easychair.org.

Organizers

- Luis Gustavo Nonato, Universidade de São Paulo, Brazil

- Filip Sadlo, Heidelberg University, Germany

Invited Speaker: Fabio Miranda

Miranda is an Assistant Professor at the Department of Computer Science at the University of Illinois Chicago. He is interested in developing techniques that allow for the interactive visual analysis of large-scale data, combining methods from visualization, data management, machine learning, and computer graphics. In particular, he focuses on how visual data analytics can help address different problems cities face by integrating data with different resolutions and from different sources. He has worked closely with domain experts from different fields, including urban planning, architecture, and public health. The outcomes of these collaborations included not only research published in visualization, database, and artificial intelligence venues, but also systems that were made available to experts in academia, industry, and government agencies.

Title: Visualizing Environmental Justice Conditions of Overburdened Communities

Abstract: According to environmental justice principles, environmental degradation should not disproportionately impact communities. Overburdened communities are those where environmental burdens (e.g., high pollution, proximity to hazardous facilities) and socioeconomic disparities (e.g., low income or minority status) act cumulatively to produce harmful living conditions. Identifying disparities in the spatial distribution of environmental degradation is therefore a prerequisite for validating the state of environmental justice in a geographic region. Under ideal circumstances, environmental risk assessment is a preferred metric, but only when exposure levels have been quantified reliably after estimating the risk. Visualization systems are critical to design environmental justice policy interventions, where stakeholders can identify overburdened communities by linking burdens and socioeconomic disparities on a map. However, there is great variation in how these systems measure and visualize both burden and disparities, leading to different approaches to identify overburdened communities and making environmental justice data accessible to the public. In this talk, I will 1) present a series of systems developed by a multidisciplinary team of researchers that use a community-based participatory design approach involving the southwest communities of Chicago, and 2) highlight visualization research opportunities related to environmental justice.

Schedule

9:00 - 9:15 Opening (Luis Gustavo Nonato)

9:15 - 10:15 Invited Speaker: Fabio Miranda

10:15 - 10:30 break

10:30 - 11:00 Tiago da Silva and Jorge Poco

Title: Automatic redesign of societally injudicious colormaps in visualizations

Abstract: The use of colors in visualizations is widely used nowadays. However, inappropriate use of colors can lead to misinterpretation of the results. This problem is even worse for visually impaired people. We propose a method to identify and automatically redesign visualizations encoding data using colors. On the one hand, this mechanism allows the automatic redesign of visualizations that may be inscrutable or offensive to certain social groups, such as the visually impaired or the culturally sensitive. On the other hand, it equips researchers and journalists with an exploratory tool to massively assess the accessibility of color maps in large corpora of graphics. This task is essential to properly recommend procedures to improve the amenity of visualizations in specific communities. Moreover, our automated approach improves the semantic characterization of color maps in graphs by exploiting the textual features of graphs. This is a preeminent operation in properly communicating visually encoded statistical data attributes to visually impaired people.

14:00 - 14:30 Thales Vieira

Title: Crime prediction and prevention using police patrolling data: challenges and prospects

Abstract: Spatiotemporal crime analysis and prediction aim at identifying criminal patterns in space and time. In previous work, crime prediction has been performed by identifying hotspots from data, which means areas of high criminal activity on the streets. By focusing efforts on such sites, police patrolling is expected to be more efficient, thus reducing criminal activity. However, there is a lack of studies investigating how police patrolling affects crime, and whether it can be a predictor of crime activity. In this paper we discuss the main challenges of this problem, and describe some work in progress towards developing a robust methodology to represent, visually analyze, and build predictors for criminal activity, considering both criminal and police patrolling spatiotemporal data. As a case study, we use real datasets from the Military Police of the state of Alagoas, Brazil (PM-AL).

14:30 - 15:00 Germain Garcia-Zanabria

Title: SDA-Vis: A Visualization System for Student Dropout Analysis Based on Counterfactual Exploration

Abstract: High and persistent dropout rates represent one of the biggest challenges for improving the efficiency of the educational system, particularly in underdeveloped countries. A range of features influences college dropouts, with some belonging to the educational field and others to non-educational fields. Understanding the interplay of these variables to identify a student as a potential dropout could help decision-makers interpret the situation and decide what they should do next to reduce student dropout rates based on corrective actions. In this presentation, I will present SDA-Vis, a visualization system that supports counterfactual explanations for student dropout dynamics, considering various academic, social, and economic variables. In contrast to conventional systems, our approach provides information about feature-perturbed versions of a student using counterfactual explanations. SDA-Vis comprises a set of linked views that allow users to identify variables alteration to chance predefined student situations.

15:00 - 15:15 break

15:15 - 16:00 Panel: How can visualization help solve urban problems?

Chair: Filip Sadlo

Panelists: Claudio Silva (New York University - USA), Jorge Poco (Fundacao Getulio Vargas - BR), and Fabio Miranda (University of Illinois - USA)