Students collaborating on a project

DSPG Young Scholars Program Brings the Biocomplexity Institute’s Culture of Mentorship to Life Again This Summer

University of Virginia students and Virginia natives Trinity Chamblin and Anjali Mehta have a unique opportunity this summer to help shape the future of the community they call home. Chamblin, who was born and raised in Virginia’s Fairfax County, and Mehta, who was raised in Woodbridge and moved to Fairfax County in 2019, received this opportunity as part of the UVA Biocomplexity Institute’s annual Data Science for the Public Good (DSPG) Young Scholars program, which kicked off on Memorial Day and spans through early August.

DSPG Young Scholars, now in its 10th year, brings undergraduate and graduate students together from across the country for 10 weeks throughout the summer to engage with research projects that address local, state, and federal government challenges around critical social issues. The students conduct research at the intersection of statistics, computer science, and the social sciences to determine how data can be leveraged for the public good. DSPG Young Scholars aims to equip a new generation of scientists with the skills to inform public policy and decision making around complex problems that impact people’s lives in real and meaningful ways.

Chamblin and Mehta are among nine students selected for this year’s program. Each DSPG Young Scholar supports two projects from the Biocomplexity Institute’s ongoing research collaborations. Among them this year is the Institute’s work with the Mastercard Center for Inclusive Growth to develop an open curated knowledge repository called the Social Impact Data Commons (SIDC). The SIDC co-locates data from a variety of sources including public datasets, administrative records, and private entities and integrates analytical tools that enable local government officials and community leaders to use real-time, geographically relevant data to inform their decision making.

The Institute team has initially developed the SIDC with the goal of informing equitable growth and helping solve specific, pressing local issues for localities in the Washington, D.C. metropolitan region. The work began in Virginia’s Arlington County where the Institute team partnered with county officials to better understand social impact issues through data including equity of broadband access and access to staple foods. Now, the team has expanded its scope to include Virginia’s Fairfax County, where they are tackling a broad range of issues including the analysis of minority business ownership across industries, cost of living for families, food insecurity, and the well-being of girls and women in the county.

Chamblin and Mehta elected to work on the minority business ownership project in which Fairfax County officials are seeking to better understand the impact that the COVID-19 pandemic had on small- and minority-owned businesses across the country and identify specific business sectors or types of businesses that continue to struggle. Most of the data Fairfax County officials previously had access to was outdated, did not reflect current economic conditions nor provide details of key groups such as sole proprietorships or minority ownership.

"The Fairfax County government would like to understand how many small- and minority-owned businesses there are in the county, how that number has changed over time, and possibly predict how it will change in the future," Mehta said. "Our goal is to build a Natural Language Processing model that can be used to analyze and assess the conditions of the businesses in a particular industry."

Through the SIDC, the Institute team will be able to provide Fairfax County officials with the ability to map trends through time by business type. With this data, they will have better information to craft policy and interventions to address the current and future needs of the business community and direct assistance to areas with the greatest need.

Mehta continued, "Thinking about the impact of the work is very important to me – especially because my parents are soon opening a small minority-owned business in Fairfax County. We are opening a dog daycare and boarding facility called 'The Dog Stop.' After learning about the [SIDC] project and the direct benefits it could have on my community and family…I knew that I wanted to be directly involved. Being involved at such a high level – performing data analysis that the local government will directly use – is extremely exciting."

"Being involved in work that has the potential to directly impact my home community means a great deal to me," Chamblin added. "This project allows me to channel my personal experiences into actionable solutions. By emphasizing equity and cultural understanding, I aim to contribute to addressing the unique challenges faced by underserved communities, including my own. This work is not just an abstract concept for me; it represents a tangible opportunity to uplift the voices and experiences of those who have historically been marginalized."

Other projects that the DSPG Young Scholars are supporting this year include:

  • Biokind Analytics – An effort to bring data science to healthcare-focused non-profit organizations to help further their missions
  • Army Research Institute for the Behavioral and Social Sciences – Examining Soldier career progression and performance
  • U.S. Census Bureau – Evaluating methods and assessing the data needs of local communities and states by examining state constitutions and amendments and outputs from U.S. Census Bureau-funded State Data Centers and Census Information Centers
  • U.S. Department of Agriculture Economic Research Service – Assessing the impact of broadband development programs in rural America

A hallmark of the DSPG Young Scholars program is its mentoring-focused structure, which is inspired by the Biocomplexity Institute’s culture of mentoring that strives to shape the next generation of outstanding scientists. Students work in collaborative, vertically and horizontally integrated teams alongside postdoctoral associates, research faculty, and support staff from the Institute. They receive individualized, interdisciplinary mentorship by multiple division researchers, and unique opportunities to interact with decision makers from across community groups, industry, and government agencies.

"The program's team science approach and mentoring structure have played a significant role in shaping the work I have been doing so far," Chamblin said. "The Institute mentors, who are experienced researchers and experts in the field, have provided invaluable guidance, advice, and feedback throughout the research process and have always been available to answer my questions. With a set interest in data science, working at the Institute has allowed me to start thinking about some of the topics I'm interested in and the problems I want to help solve. It's helped me develop a deeper understanding of the field and nurtured an environment for my continuous learning."

Over the last 10 years, more than 100 hundred students have participated in the DSPG Young Scholars program. Six of this year’s scholars are from UVA, and the remaining three hail from Carleton College, Carnegie Mellon University, and San Diego State University. The program includes seven women and two men with diverse population backgrounds.

"We tried to be more mindful and targeted in our promotion to reach more diverse audiences and to branch out beyond UVA," said Joel Thurston, senior scientist and research manager in the Institute's Social and Decision Analytics Division (SDAD) who has helped lead the DSPG Young Scholars program for the last four years. "We want to get the opportunity in front of groups that have traditionally been underrepresented in the computer science, data science, and math fields. We made some initial strides toward that goal this year and will continue that effort in years ahead."

Throughout the summer, the program will welcome a variety of guest speakers from organizations including the Fairfax County Government, Methodspace, Microsoft, the UN Refugee Agency, Urban Institute, and the U.S. Census Bureau along with a DSPG Young Scholars alumnus from The Data Center in New Orleans.

As the DSPG Young Scholars program marks its 10th year, alumni are making an immeasurable impact on the current generation of participants. For the first time ever, a student – Carleton College undergraduate Sara Shallenberger – was introduced to the program by her statistics professor and 2017 DSPG Young Scholars alumnus Claire Kelling. Shallenberger is the first second-generation DSPG Young Scholar – another remarkable demonstration of the program’s mentoring ethos.

"It's a very powerful message for our students to hear from people who are relatively close in age to them and see how successful they have been after being in DSPG Young Scholars and the difference it has made in their careers," said Cesar Montalvo, SDAD research assistant professor and co-lead of the DSPG Young Scholars program. "We have invited alumnus Haleigh Tomlin from The Data Center to speak this year. She studied poverty in communities and learned how to identify poverty trends in neighborhoods. After graduation, she applied for a position that sought someone with her exact skillset and experience – it was the perfect fit. I am so glad that she has taken this pathway, but even more, that she can inspire others with what she is doing. This progression can have a substantial impact on different groups, especially minority groups that are not used to seeing people like them in these fields. Programs like DSPG can have an immense effect."

The program will culminate with the DSPG Symposium on August 3 where the 2023 scholars will present the output of their research projects. Learn more about the Biocomplexity Institute’s DSPG Young Scholars program here.