Published by 112 co-authors in the Proceedings of the National Academy of Sciences, the results suggest that sociologists and data scientists should use caution in predictive modeling, especially in the criminal justice system and social programs.
Every day, Virginia Tech faculty, researchers, and students delve into data, experiment, and study research findings to address real-world challenges. In the latest installment on complex problems, hear how data is used to boost safety, improve efficiency, and promote equity.
Sengupta, assistant professor of statistics in the College of Science and a faculty member at the Discovery Analytics Center, received a Research Project Grant to develop methods to analyze detailed information that spans multiple categories and can be more valuable in identifying an event than just checking off a category.
The Ph.D. student and National Science Foundation research trainee in the multidisciplinary UrbComp program, administered through the Discovery Analytics Center, will compare online and offline social networks to provide urban planners and local leaders with insights and expanded tools to increase the voice and visibility of historically marginalized citizens.
The assistant professor of computer science and a faculty member at the Discovery Analytics Center is also one of only two women to receive the Social Media and Democracy Research Grant. Mitra and her team will study how misinformation and other problematic content spread on the platform.
With the award, Jia-Bin Huang will tackle challenges of modeling the relationship between a person and relevant objects/scene to gather contextual information and mining hard examples automatically from unlabeled but interaction-rich videos.
While other research focuses almost exclusively on situations where group identities of users are known, Bert Huang, professor of computer science and a faculty member at the Discovery Analytics Center, and Ph.D. student Sirui Yao look at settings where they do not know, or do not trust, information about who belongs to what groups.
An online interactive platform developed at the Discovery Analytics Center uses data analytics and machine learning to help stakeholders better understand school rezoning plans and potential effects on the community. Users can also share comments and concerns about proposed plans, propose changes to boundaries, and even create their own plans.