DSPG Annual Symposium 2020

DATA SCIENCE FOR THE PUBLIC GOOD ANNUAL SYMPOSIUM 2020

August 7, 2020 – 1:00pm

*Note: These events are being recorded by audio, video, and photographic means. By attending, you grant the University of Virginia the right to use your voice/likeness in any depiction of these events.

DSPG AudiencePlease join us for our annual Data Science for the Public Good Symposium to be hosted virtually featuring keynote speaker Kenneth Prewitt, Carnegie Professor of Public Affairs and Special Advisor to the President, and this year’s DSPG Young Scholars.

Thanks to a grant from the USDA, the DSPG Young Scholars program was able to expand beyond the Commonwealth of Virginia for the first time to create a three-state Coordinated Innovation Network among five partner universities: Oregon State University, Iowa State University, Virginia Tech, University of Virginia, and Virginia State University.

As a result, this year’s DSPG Symposium brings over 60 undergraduate and graduate students together with postdoctoral fellows and faculty to present 30 research projects that address critical social issues relevant in the world today.

Date: August 7, 2020
Time: 1-4:30 p.m. ET

Keynote Speech Video

Posters

In a normal world, in-person attendees would be invited to circulate the poster sessions and interact with young scholars as they discussed their research projects. This year, as you know, nothing is normal; and we’re trying to simulate the same experience in a virtual setting. Our young scholars have worked really hard this summer to deliver public good, and would love to share their research in their virtual “zoom rooms” after the plenary session. (Zoom links will be shared with registered attendees on the day of the Symposium.)

Before the Symposium, learn more about each research project, including brief overview, teaser video, and students involved, by following the links below. On the day of the event, join the zoom room for each project using the links that will be provided to registered attendees.

1. The American Soldier in World War II: Extracting Insights from Historical Textual Data

The DSPG project aims to analyze textual data produced as part of The American Soldier in World War II, a federally funded, multi-institutional digital history project which is designed to raise public awareness on the experiences of World War II American GIs. The project harvests data from a unique and historic collection that was produced by the U.S. Army during the war, “attitude surveys” that were administered to hundreds of thousands of American troops. The DSPG team analyzes soldiers’ handwritten responses by using natural language processing methods and social network analysis to dive into soldiers’ attitudes about other social groups (groups to which they did not themselves identify), ethnic and racial relations as well as gender relations.

Fellows:

Morgan Elaine Stockham, Claremont Graduate University, Applied Microeconomics

Mary Solomon, Bowling Green State University, Applied Statistics

Interns:

Saimun Habib, Harvard College, Statistics

Chase Dawson, University of Virginia, Computer Science

Mentors:

Gizem Korkmaz, Research Associate Professor, Biocomplexity Institute, University of Virginia

Brandon Kramer, Postdoctoral Associate, Biocomplexity Institute, University of Virginia

Stakeholder:

Ed Gitre, Assistant Professor, Virginia Tech Department of History

External Collaborators:

Mark Embree, Professor of Mathematics, VT Department of Mathematics, and Director of Computational Modeling & Data Analytics (CMDA)

Savannah Amos, Virginia Tech Computational Modeling & Data Analytics (CMDA)

Yash Joshi, Virginia Tech Computational Modeling & Data Analytics (CMDA)

Drew Klaubert, Virginia Tech Computational Modeling & Data Analytics (CMDA)

Stakeholder: Virginia Tech Department of History

Project Website Video

2. Army Performance Measurement: Content and Themes

This project examines the feasibility of measuring Soldier performance with information contained in the Army’s Person-Event Data Environment (PDE) data repository by analyzing existing performance metrics. This is a necessary first step towards modeling of relationships between social characteristic variables and performance outcome. To facilitate this, the team has collected performance scales from a variety of sources to evaluate using different text analysis techniques.

Fellows:

Daniel Bullock, Indiana University Bloomington, Cognitive Neuroscience

Interns:

Liz Miller, William & Mary, International Relations

Gina Fendley, Marymount University, Philosophy

Mentors:

Nathaniel Ratcliff, Research Assistant Professor, Biocomplexity Institute, University of Virginia

Joel Thurston, Senior Scientist, Biocomplexity Institute, University of Virginia

Stakeholder:

Dr. Kelly Ervin, U.S. Army Research Institute for the Social and Behavioral Sciences

Stakeholder: U.S. Army Research Institute for the Social and Behavioral Sciences

Project Website Video

3. Modeling Career Pathways of Veterans in the DC Metro Area

This project focuses on exploring the career pathways of Army veterans, observed using Burning Glass Technologies resume data. The team explores modeling techniques including sequence analysis and tournament models to classify resume data into a typology of career trajectories, and identify factors associated with career mobility. Initial modeling efforts are focused on resumes in the Washington Metropolitan area.

Fellows:

Maddie Pickens, Georgetown University, Data Science for Public Policy

Interns:

Joanna Schroeder, William & Mary, Government

Crystal Zang, Smith College, Mathematics, Statistical & Data Science

Mentors:

Joshua Goldstein, Assistant Research Professor, Biocomplexity Institute, University of Virginia

Stakeholder: U.S. Army Research Institute for the Behavioral and Social Sciences

Project Website Video

4. Sectoring Open Source Software: Where Do GitHub Contributions Come From?

Our project aims to measure how much open source software is in use, how much is created, who is developing these tools, and how such tools are being shared across different sectors, institutions, and organizations. Building on past research, our team used data scraped from GitHub – the world’s largest remote hosting platform – to classify users into academic, government, and business sectors using natural language processing and by joining multiple publicly available data sources. In turn, we used social network analysis to analyze collaborations within and across these sectors to better understand how open source software tools are developed across the globe.

Fellows:

Daniel Bullock, Indiana University Bloomington, Cognitive Neuroscience

Interns:

Morgan Klutzke, Indiana University, Psychology and Cognitive Science

Crystal Zang, Smith College, Mathematics, Statistical & Data Science

Mentors:

Gizem Korkmaz, Research Associate Professor, Biocomplexity Institute, University of Virginia

Brandon Kramer, Postdoctoral Associate, Biocomplexity Institute, University of Virginia

J Bayoán Santiago Calderón, Postdoctoral Associate, Biocomplexity Institute, University of Virginia

Stakeholder:
Carol Robbins, Senior Analyst, National Center for Science and Engineering Statistics, Science and Engineering Indicators

Stakeholder: NSF National Center for Science and Engineering Statistics, Science and Engineering Indicators

Project Website Video

5. Detecting and Linking Pharmaceutical Innovators in News Articles

We study the landscape of product innovation in the pharmaceutical sector (drugs and medical devices) that is heavily regulated by the Food and Drug Administration (FDA). The non-traditional data sources include publicly available opportunity and administrative data such as drug approvals and listings as well as news articles obtained from Dow Jones, a business news and data provider. We implement natural language processing methods and fuzzy matching techniques to identify innovators and use our findings to study how innovators might participate in the product development pipeline as reflected by these novel data sources.

Fellows:

Susweta Ray, University of Nebraska-Lincoln, PhD in Agricultural Economics, Statistics

Interns:

Isabel Gomez, Smith College, Statistical and Data Science

Ian MacLeod, The University of Mary Washington, Computer Science

Mentors:

Gizem Korkmaz, Research Associate Professor, Biocomplexity Institute, University of Virginia

Devika Mahoney-Nair, Research Scientist, Biocomplexity Institute, University of Virginia

Neil Alexander Kattampallil, Research Scientist, Biocomplexity Institute, University of Virginia

Stakeholder:

Gary Anderson, Senior Science Resources Analyst, National Center for Science and Engineering Statistics, Research & Development Statistics Program

Stakeholder: NSF National Center for Science and Engineering Statistics, Research & Development Statistics Program

Project Website Video

6. Skilled Technical Workforce (STW) Estimates for States x Years (2010 to 2019) and Benchmarking

A job in the skilled technical workforce (STW) is one that is open to an individual without a bachelor’s degree who has a high level of knowledge in a technical domain. The United States needs a STW to foster innovation and remain competitive in the global economy, but projections estimate 3.4 million unfilled STW jobs by 2022. This project explores ways to fill the data deficit on the STW by evaluating the fitness-for-use of the Burning Glass Technologies job-ad data for describing the employer demand for STW jobs.

Fellows:

Sarah McDonald, Marymount University, Economics and Mathematics

Interns:

Gina Fendley, Marymount University, Economics and Philosophy

Ian MacLeod, The University of Mary Washington, Computer Science

Mentors:

Vicki Lancaster, Principal Scientist, Biocomplexity Institute, University of Virginia

J Bayoán Santiago Calderón, Postdoctoral Associate, Biocomplexity Institute, University of Virginia

Stakeholder:

Gigi Jones, Project Officer, Skilled Technical Workforce and National Training, Education, and Workforce Survey, National Center for Science and Engineering Statistics (NCSES)

Stakeholder: NSF National Center for Science and Engineering Statistics

Project Website Video

7. RnD Abstracts: Emerging Topic Identification

This goal of this project is to identify emerging research topics across time utilizing topic models and visualization techniques. The data utilized for this project is a corpus of Research and Development abstracts that is publicly available from Federal RePORTER. We built on prior work for this project by adding the 2019 data to our dataset and using the topic modeling techniques of Latent Dirichlet Allocation and Nonnegative Matrix Factorization. Using these topic model results we employed an emerging topic strategy to determine which topics are gaining (or waning) in popularity over time. We also created a dashboard for users to interact with topic model results and even create their own topic models about specific areas of interest, for example, pandemics.

Fellows:

Lara Haase, Carnegie Mellon University, MS in Public Policy and Management – Data Analytics

Interns:

Martha Czernuszenko, The University of Texas at Austin, Information Systems & Canfield Business Honors Program

Liz Miller, William & Mary, International Relations

Sean Pietrowicz, University of Notre Dame, Applied and Computational Mathematics and Statistics

Mentors:

Kathryn Linehan, Research Scientist (Project Lead), Biocomplexity Institute, University of Virginia

Eric Oh, Research Assistant Professor, Biocomplexity Institute, University of Virginia

Stephanie Shipp, Deputy Division Director and Research Professor, Biocomplexity Institute, University of Virginia

Joel Thurston, Senior Scientist, Biocomplexity Institute, University of Virginia

Stakeholders:

National Center for Science and Engineering Statistics, Research & Development Statistics Program:
– John Jankowski, Program Director
– Audrey Kindlon, Survey Statistician
– Chris Pece, Senior Analyst
– Ronda Britt, Senior Analyst
– Gary Anderson, Senior Science Resources Analyst

Stakeholder: NSF National Center for Science and Engineering Statistics, Research & Development Statistics Program

Project Website Video

8. Evaluating Residential Property Data Quality

To explore the influence of broadband access on rural property values, this project evaluates the quality of CoreLogic property data, which is aggregated commercial and residential property data based on county tax assessments and property deeds. We are comparing American Community Survey estimates to CoreLogic counts and estimates for relevant housing variables. Property-level comparisons at the national level would not be possible without access to the underlying local data. We additionally focus on two Virginia counties for which we have local property-level data, Fairfax County and New Kent County, as case studies for additional data quality evaluations. This project will enable the Social and Decision Analytics team and other CoreLogic data users to learn about the strengths and limitations of CoreLogic data.

Fellows:

Maddie Pickens, Georgetown University, Data Science for Public Policy

Interns:

Morgan Klutzke, Indiana University, Psychology and Cognitive Science

Vatsala Ramanan, Smith College, Quantitative Economics

Mentors:

Stephanie Shipp, Deputy Division Director and Research Professor (Project Lead), Biocomplexity Institute, University of Virginia

Devika Mahoney-Nair, Research Scientist, Biocomplexity Institute, University of Virginia

Neil Alexander Kattampallil, Research Scientist, Biocomplexity Institute, University of Virginia

Josh Goldstein, Associate Research Professor, Biocomplexity Institute, University of Virginia

Aaron Schroeder, Associate Research Professor, Biocomplexity Institute, University of Virginia

Stakeholder:
John Pender, Economist, USDA Economic Research Service, Rural Liaison, Rural Economy Branch

Stakeholder: US Department of Agriculture, Economic Research Service

Project Website Video

9. Fairfax County Labor Markets: Characterizing Local Workforce and Employment Networks

This project explores labor markets in Fairfax County, VA to better understand the landscape and barriers to economic opportunity for the county’s residents, businesses, and places. Our project has three goals: characterize the Fairfax County workforce, occupation sectors, and industry composition; identify areas that are vulnerable, and areas that have the potential to create emerging businesses; and map workforce flows within and in/out of Fairfax County by select occupation and industry factors. Our findings can inform Fairfax County COVID response and provide insights into workforce readiness, economic vibrancy, and industry diversification, contributing to the county’s strategic plan goal of improving economic opportunity in the area.

Fellows:

Susweta Ray, University of Nebraska-Lincoln, Agricultural Economics

Interns:

Sarah McDonald, Marymount University, Mathematics and Economics

Owen Hart, University of California Berkeley, Economics and Data Science

Sean Pietrowicz, University of Notre Dame, Applied and Computational Mathematics and Statistics

Mentors:

Teja Pristavec, Research Assistant Professor, Biocomplexity Institute, University of Virginia

Brandon Kramer, Postdoctoral Research Associate, Biocomplexity Institute, University of Virginia

Stakeholders:

Fairfax County Government: Michelle Gregory, Sophia Dutton

Stakeholder: Fairfax County Government

Project Website Video

10. Assessing factors of Economic Mobility through a Political Capital lens

Our long-term project goal is to provide communities with opportunities to extract data insights, develop capacity to meet their current needs and prepare for the future. Guided by the Community Capitals framework, we investigated “Political Capital” by conducting an extensive literature review to uncover policy domains that have potential to impact economic mobility. Domains we focused on: Employment, Voting, Housing & Zoning, Education, Policing, and Taxation. Within each, we collected data on policies and laws for Virginia, Iowa, and Oregon. We created an interactive dashboard that allows users to see visualizations of the data and explore by domain and state.

Fellows:

Lara Haase, Carnegie Mellon University, MS in Public Policy and Management – Data Analytics

Interns:

Vatsala Ramanan, Smith College, Quantitative Economics

Martha Czernuszenko, The University of Texas at Austin, Information Systems & Canfield Business Honors Program

Riya Berry, UC Berkeley, Data Science & Interdisciplinary Studies

Tasfia Chowdhury, Indiana University Bloomington, Major: Political Science

Mentors:

Vicki Lancaster, Principal Scientist, Biocomplexity Institute, University of Virginia

Cesar Montalvo, Research Associate, Biocomplexity Institute, University of Virginia

Stakeholders:
The Gates Foundation
Land Grant Universities – Cooperative Extension Program
– Mike Lambur, Virginia Tech, Asso. Dir. of Program Dev. for VA Cooperative Extension Service
– Cassandra J. Dorius, Iowa State U., Associate Prof of Human Development and Family Studies
– Stuart Reitz, Oregon State University Professor and Director of the Malheur Experiment Station

Stakeholder: The Gates Foundation and Land Grant Universities – Cooperative Extension Program

Project Website Video

11. Barriers to Health Care Access and Use in Patrick County, VA

This project provides data-driven insights for Patrick County in addressing barriers to health for its residents. We worked closely with stakeholders to identify lack of data on health care access, food access as related to diabetes and heart disease prevalence, older adult health, and digital connectivity that would facilitate access to telemedicine as key problems where providing insights could inform decision-making to improve county residents’ quality of life. The team used publicly available data to provide actionable information in each of the four areas, identifying emergency medical service station coverage gaps, food deserts, areas of high older adult need, and broadband gaps. Our findings will allow the sponsor to better understand health care provision options for its residents, identify the characteristics of equity and health disparities across the county, and design solutions targeting barriers to health at the neighborhood level.

Fellows:

Morgan Stockham, Claremont Graduate University, Applied Microeconomics

Interns:

Isabel Gomez, Smith College, Statistical and Data Science

Tasfia Chowdhury, Indiana University Bloomington, Political Science

Mentors:

Teja Pristavec, Research Assistant Professor, Biocomplexity Institute, University of Virginia

Stakeholders:

Patrick County Extension Office and Virginia Department of Health
Terri Alt, Patrick County Extension Office
Nancy Bell, Virginia Department of Health

Stakeholders: Patrick County Extension Office and Virginia Department of Health

Project Website Video

12. Halifax County: Factors of Incarceration and Recidivism

Halifax County has partnered with DSPG 2020 to investigate the factors associated with its incarceration and recidivism rate in the hopes of investing in proactive services through the Virginia Cooperative Extension Service. This project seeks to synthesize various public data sources that may help characterize the state of various social determinants of incarceration and recidivism in Halifax county and identify gaps in data collection that, if filled, could help provide a more comprehensive view of what is a complex and nuanced issue.

Fellows:

Finn Roberts, University of Minnesota, MS in Biostatistics and Geographic Information Systems

Interns:

Ellen Graham, Macalester College, Applied Mathematics and Statistics, Computer Science

Riya Berry, UC Berkeley, Data Science & Interdisciplinary Studies

Mychala Walker, Virginia State University, Political Science

Mentors:

Nathaniel Ratcliff, Research Assistant Professor, Biocomplexity Institute, University of Virginia

Joel Thurston, Senior Scientist, Biocomplexity Institute, University of Virginia

Alyssa Mikytuck, Postdoctoral Researcher, Biocomplexity Institute, University of Virginia

Eric Oh, Research Assistant Professor, Biocomplexity Institute, University of Virginia

Stakeholders:

Sonya Furgurson, District Director, Halifax Central
Hunter Martin

Stakeholders: Halifax Central District Director

Project Website Video

13. Economic Mobility Baseline and Comparative Analysis for the South Wasco County School District Area, Oregon

South Wasco County, Oregon, located in the state’s north central border, experienced significant economic decline in the 1980s driven largely by the loss of timber industry. This was followed by closure of schools and consolidation of students from school districts and an out-migration of residents that disrupted economic stability, community health, and quality of life. Working together the regional Cooperative Extension professional, an NGO Coordinating Stakeholder from the South Wasco Alliance and University of Virginia researchers are evaluating methods to construct economic mobility models and adjust the approach for application in a rural environment. To do this, they are discovering, inventorying, profiling, and documenting the data sources and their fitness-for-use, to inform barriers to economic mobility. These include indicators focused on local and regional food systems, tourism, and light manufacturing. The outputs will be creation of economic mobility datasets presented in an interactive dashboard to support local decision-making.

Fellows:

Mary Solomon, Bowling Green State University, Mathematics and Statistics

Interns:

Joanna Schroeder, William & Mary, Government

Owen Hart, University of California Berkeley, Economics and Data Science

Mentors:

Aaron Schroeder, Research Associate Professor, Biocomplexity Institute, University of Virginia

Alyssa Mikytuck, Postdoctoral Research Associate, Biocomplexity Institute, University of Virginia

Eric Oh, Research Assistant Professor, Biocomplexity Institute, University of Virginia

Stakeholder:

Kathleen Willis
South Wasco Alliance

Stakeholder: South Wasco Alliance

Project Website Video

14. Understanding the Impact of COVID-19 on the Delivery of Emergency Medical Services

The Charlottesville Fire Department, the Albemarle County Department of Fire and Rescue and the University of Virginia are working together to understand how the Covid-19 pandemic is impacting their combined communities, with particular emphasis on the delivery of Emergency Medical Services (EMS). In addition to describing how EMS operations have changed when compared to operations prior to the epidemic (e.g. call volume, distribution of dispatch types, EMS provider impressions, EMS patient dispositions), particular attention will be given to changes in EM service delivery and needs in “at-risk” populations in the response areas.

Fellows:

Finn Roberts, University of Minnesota, MS in Biostatistics and Geographic Information Systems

Interns:

Chase Dawson, University of Virginia, Computer Science

Ellen Graham, Macalester College, Applied Mathematics and Statistics, Computer Science

Saimun Habib, Harvard College, Statistics/Mathematics

Mentors:

Aaron Schroeder, Research Associate Professor, Biocomplexity Institute, University of Virginia

Joy Tobin, Principal Scientist, Biocomplexity Institute, University of Virginia

Gizem Korkmaz, Research Associate Professor, Biocomplexity Institute, University of Virginia

Kathryn Linehan, Research Scientist, Biocomplexity Institute, University of Virginia

Stakeholders:

Emily Peliccia, Interim Fire Chief, Charlottesville Fire Department

Dan Eggleston, Chief EFO/CFO/CMO, County of Albemarle, Department of Fire Rescue

Michael Williams, Associate Professor of Surgery, The University of Virginia Medical School

Stakeholders: Charlottesville Fire Dept.; Cty. of Albemarle, Dept. of Fire Rescue; The UVA School of Medicine

Project Website Video

15. Industry and Workforce Attraction and Retention in Wythe County

Wythe County wants to understand why companies locate where they do and what the county can do to be more competitive. The county faces the same challenges as other rural counties – declining population, poor broadband coverage, drug addiction, and a high poverty rate. To address these issues, they would like to increase their job opportunities. Located in southwestern Virginia, with a population around 29,000, the Executive Director of the county’s Joint Industrial Development Authority (JIDA), wants to identify factors that would improve Wythe’s attractiveness to companies. The Virginia Cooperative Extension agent and Virginia Tech researchers are investigating factors that affect Wythe’s ability to attract companies, as well as the benefits and costs of the Wythe industrial park.

Fellows:

Josh Beverly, Virginia Tech, Agricultural and Applied Economics

Interns:

Adam Wells, Virginia Tech, Data Analysis and Applied Statistics

Afrina Tabassum, Virginia Tech, Computer Science

Dylan Glover, Virginia Tech, Mathematics

Mentors:

Susan Chen, Associate Professor, Agricultural and Applied Economics, Virginia Tech

Ford Ramsey, Assistant Professor, Agricultural and Applied Economics, Virginia Tech

Conaway Haskins, Extension Specialist, Agricultural and Applied Economics, Virginia Tech

Stakeholder:

Virginia Cooperative Extension

Stakeholder: Virginia Cooperative Extension

Video

16. Measuring Economic and Social Infrastructure: Intergenerational Poverty in Page County

Page County has a significant population of incarcerated residents in recovery with few employment opportunities available. Located in a largely agricultural area in northeast Virginia, the Page County Economic Development Community Action Team is interested in starting an agricultural-based social enterprise that would work with residents to acquire skills and jobs. They would like to understand the practicality of this goal before applying for grants to start the social enterprise. The Page Count Cooperative Extension agent and Virginia Tech researchers are creating data insights to identify the areas to assist Page County’s formerly incarcerated residents, including alleviating food insecurity, homelessness, low job skills, and substance abuse recovery.

Fellows:

Josh Beverly, Virginia Tech, Agricultural and Applied Economics

Interns:

Talib Grant, Virginia Tech, Data Analytics

Laura Pranteddu, Virginia Tech and University of Trento, Data Science

Afrina Tabassum, Virginia Tech, Computer Science

Mentors:

Susan Chen, Associate Professor, Agricultural and Applied Economics, Virginia Tech

Ford Ramsey, Assistant Professor, Agricultural and Applied Economics, Virginia Tech

Conaway Haskins, Extension Specialist, Agricultural and Applied Economics, Virginia Tech

Stakeholder:

Virginia Cooperative Extension

Stakeholder: Virginia Cooperative Extension

Video

17. Measuring Regional Food Insecurity and the Role of a Loudon County Food Hub

Although Loudoun County has the highest average income in the United States, they have a significant population that is food insecure. Loudoun is largely rural, with the majority of its 425,000 residents concentrated in the eastern part of the county. Health Services Strategic Plan Advisory Committee wants to assess the feasibility of creating a food hub that connects schools, restaurants and the community to increase the availability and quality of food to their those that cannot afford or have access to healthy food. The Advisory Committee, composed of representatives from several social service agencies, and community organizations, believes the food hub will improve community engagement, social cohesion, civic participation, and cultural awareness. Loudoun County’s Cooperative Extension Agent and Virginia Tech researchers are examining food hubs in the Charlottesville and other areas as well as creating data-driven profiles of Loudoun County’s low-income populations to inform the feasibility of creating a food hub.

Fellows:

Boya Zhang, Virginia Tech, Statistics

Interns:

Laura Pranteddu, Virginia Tech and University of Trento, Data Science

Talib Grant, Virginia Tech, Data Analytics

Adam Wells, Virginia Tech, Data Analysis and Applied Statistics

Mentors:

Susan Chen, Associate Professor, Agricultural and Applied Economics, Virginia Tech

Ford Ramsey, Assistant Professor, Agricultural and Applied Economics, Virginia Tech

Conaway Haskins, Extension Specialist, Agricultural and Applied Economics, Virginia Tech

Stakeholder:

Virginia Cooperative Extension

Stakeholder: Virginia Cooperative Extension

Video

18. Understanding Evictions in Richmond City: Policy, Community, and Individual Factors

Richmond City has the highest eviction rate in Virginia and is in the top 10 in the country. More than one out of four of the 221,000 Richmond City residents are poor and many are evicted on a recurring basis. The coronavirus has exacerbated their problems. City of Richmond Treasurer’s Office Financial Education Center and the Southside Community Development and Housing Corporation’s (SCDHC) Financial Opportunity Center help families become financially literate, develop spending plans, and learn how to access and manage credit. Richmond City’s Cooperative Extensions agent and Virginia Tech researchers are using data provided by the city combined with state and federal sources of data to improve their understanding of who the city is serving, including their spending habits and whether they have enough resources to manage. The team is creating data-driven insights with the goal to improve the financial and housing stability of these families and the city.

Fellows:

Boya Zhang, Virginia Tech, Statistics

Interns:

Adam Wells, Virginia Tech, Data Analysis and Applied Statistics

Afrina Tabassum, Virginia Tech, Computer Science

Dylan Glover, Virginia Tech, Mathematics

Laura Pranteddu, Virginia Tech and University of Trento, Data Science

Mentors:

Susan Chen, Associate Professor, Agricultural and Applied Economics, Virginia Tech

Ford Ramsey, Assistant Professor, Agricultural and Applied Economics, Virginia Tech

Conaway Haskins, Extension Specialist, Agricultural and Applied Economics, Virginia Tech

Stakeholder:

Virginia Cooperative Extension

Stakeholder: Virginia Cooperative Extension

Video

19. Factors contributing to Health Care Inequities in Petersburg, VA

Petersburg, VA consistently ranks at or near the bottom of the County Health Rankings for the Commonwealth of Virginia. The Petersburg Wellness of Consortium (PWC) is a collaboration of local stakeholders with the goal of improving health outcomes for Petersburg. In order to support the PWC’s goal, this project explored how disparities in income and access to food, health care, and healthy options may relate to the health outcomes observed in Petersburg.

Fellows:

JaiDa Robinson, Virginia State University, Counselor Education

Courtney Lawson, Virginia State University, Computer Science

Interns:

Kyle Jacobs, Virginia State University, Agriculture

Mychala Walker, Virginia State University, Political Science

Reginald Toure, Virginia State University, Computer Science

Kyra Faison, University of Maryland, Baltimore County, Environmental Science

Mentors:

Sarah Witiak, Associate Professor, Biology, Virginia State University

Brian Sayre, Professor, Biology, Virginia State University

Dong Yoo, Associate Professor, Computer Information Systems, Virginia State University

Wei-Bang Chen, Associate Professor, Computer Science, Virginia State University

M. Omar Faison, Assistant Vice President, Research, Virginia State University

Stakeholder:

Petersburg Wellness Consortium

Stakeholder: Petersburg Wellness Consortium

Project Website Video

20. Demonstrating the value of Appomattox River Trail

FOLAR is local non-profit organization with a mission to “conserve and protect the Appomattox River for all to enjoy.” As a part of that mission, FOLAR is providing leadership to the development of the Appomattox River Trail, a 25 mile long trail system through the region for walking and biking. Our team explored a range of data to make arguments for developing the local walking and biking infrastructure in terms of economics, transportation, and health outcomes.

Fellows:

JaiDa Robinson, Virginia State University, Counselor Education

Courtney Lawson, Virginia State University, Computer Science

Interns:

Kyle Jacobs, Virginia State University, Agriculture

Mychala Walker, Virginia State University, Political Science

Reginald Toure, Virginia State University, Computer Science

Kyra Faison, University of Maryland, Baltimore County, Environmental Science

Mentors:

Sarah Witiak, Associate Professor, Biology, Virginia State University

Brian Sayre, Professor, Biology, Virginia State University

Dong Yoo, Associate Professor, Computer Information Systems, Virginia State University

Wei-Bang Chen, Associate Professor, Computer Science, Virginia State University

M. Omar Faison, Assistant Vice President, Research, Virginia State University

Stakeholder:

Friends of the Lower Appomattox River (FOLAR)

Stakeholder: Friends of the Lower Appomattox River (FOLAR)

Project Website Video

21. Identify Communities Ready and Able to Support Substance Use Recovery Centers

Iowa has one of the highest per capita rates of people seeking treatment for addiction, but is one of only nine U.S. states without a Recovery Community Center network to provide non-medical, non-clinical recovery support including housing, workforce training, and peer coaching. In partnership with Iowa’s Substance Use Bureau, this project worked to identify communities ready and able to develop Recovery Community Centers by cataloging, webscraping, spatially mapping, and improving awareness of existing statewide recovery resources, including transitional housing, residential and nonresidential treatment centers, drinking driver education classes, gambling treatment centers, and access to virtual and place-based substance use meetings.

Fellows:

Atefeh Rajabalizadeh, Graduate Student, Industrial Engineering, Iowa State University

Interns:

Jessie Bustin, Undergraduate Student, Data Science & Statistics, Iowa State University

Grant Durbahn, Recent Undergraduate/Incoming Graduate Student, Economics, Iowa State University

Vikram Magal, Undergraduate Student, Management of Information Systems & Business Analytics, Iowa State University

Mentors:

Shawn F. Dorius, Associate Professor of Sociology, Iowa State University

Cassandra J. Dorius, Associate Professor of Human Development and Family Studies, Iowa State University

Stakeholder:

Iowa Department of Public Health Substance Use Bureau

Program Support:

Kelsey Van Selous, MSW, LCSW, Graduate Student, Human Development and Family Studies, Iowa State University

Technical Support:

Masoud Nosrati, Department of Computer Science, Iowa State University

Stakeholder: Iowa Department of Public Health Substance Use Bureau

Project Website Video

22. Identify Communities in Greatest Need of Excessive Alcohol Prevention Efforts

Iowa ranks in the top 10 among U.S. states for binge drinking, costing roughly $635 per person in Iowa. Understanding who is at risk for excessive alcohol use and where they reside can help Iowa’s Substance Use Bureau better target prevention resources to manage alcohol-related problems. This project identified and spatially mapped the characteristics of heavy daily alcohol users, forecasted alcohol sales by county, and analyzed the prevalence of people who have been involved in car crashes after using alcohol or drugs. Interactive data tools were generated to facilitate decision making by policymakers, public health officials, and extension specialists.

Fellows:

Deepak George Thomas, Graduate Student, Computer Science, Iowa State University

Interns:

Kok Kent Chong, Undergraduate Student, Finance & Supply Chain Management, Iowa State University

Kathleen M Thompson, Recent Undergraduate/Upcoming Graduate Student, Sociology & Political Science, Iowa State University

Xinyi Zhu, Undergraduate Student, Statistics & Data Science, Iowa State University

Mentors:

Christopher J Seeger, Professor of Landscape Architecture, Iowa State University

Shawn F. Dorius, Associate Professor of Sociology, Iowa State University

Stakeholder:

Iowa Department of Public Health Substance Use Bureau

Program Support:

Ilma Jahic, Graduate Student, Sociology, Iowa State University

Technical Support:

Masoud Nosrati, Department of Computer Science, Iowa State University

Stakeholder: Iowa Department of Public Health Substance Use Bureau

Project Website Video

23. Develop a Community Capitals Data Infrastructure to Support Community Economic Mobility

Iowa’s Extension and Outreach leadership identified the need for a statewide community data infrastructure to support precision funding and targeted education in response to COVID-19. This project utilized the Community Capitals Framework to identify, collect, and spatially map county-level indicators of human, financial, natural, and social assets related to upward economic mobility. Interactive data tools were designed to support Extension leadership in identifying and monitoring the impact of COVID-19 on rural community recovery. Dashboards are intended to be paired with CES administrative files, so leaders can visually identify opportunities to more effectively match resource/programming supports with community needs.

Fellows:

Atefeh Rajabalizadeh, Graduate Student, Industrial Engineering, Iowa State University

Kishor Kumar Sridhar, Graduate Student, Information Systems, Iowa State University

Interns:

Jessie Bustin, Undergraduate Student, Data Science & Statistics, Iowa State University

Grant Durbahn, Recent Undergraduate/Incoming Graduate Student, Economics, Iowa State University

Matthew Voss, Recent Undergraduate/Upcoming Graduate Student, Statistics, Iowa State University

Vikram Magal, Undergraduate Student, Management of Information Systems & Business Analytics ,Iowa State University

Kathleen M Thompson, Recent Undergraduate/Upcoming Graduate Student, Sociology & Political Science, Iowa State University

Joel Von Behren, Undergraduate Student, Data Science, Iowa State University

Mentors:

Cassandra J. Dorius, Associate Professor of Human Development and Family Studies, Iowa State University

Todd Abraham, Assistant Director of Data & Analytics for the Iowa Integrated Data System, Iowa State University

Stakeholders:

Iowa’s Cooperative Extension and Outreach Regional Directors & University Leadership

Program Support:

Haley Jeppson, Graduate Student, Statistics, Iowa State University

Technical Support:

Masoud Nosrati, Department of Computer Science, Iowa State University

Stakeholder: Iowa’s Cooperative Extension and Outreach Regional Directors & University Leadership

Project Website Video

24. Enlarge the ISU Extension Community Helpline Services

Iowa’s Extension and Outreach program provides resources for communities, businesses, and nonprofits via six help and support hotlines. The use of hotlines has increased dramatically with the onset of COVID-19. Our team partnered with hotline managers to understand the system architecture, data structure and quality, and past uses of the data generated by the hotlines. Using this information, we piloted interactive dashboards on call topics, outcomes, and emotional content (via sentiment scoring of generated transcripts) to support improved customer service, monitor success, and auto-generate reports so hotline workers can spend more time helping citizens and less time filling out paperwork.

Fellows:

Deepak George Thomas, Graduate Student, Computer Science, Iowa State University

Interns:

Kok Kent Chong, Undergraduate Student, Finance & Supply Chain Management, Iowa State University

Andrew Maloney, Recent Undergraduate/Incoming Master’s Student, Mathematics, Iowa State University

Xinyi Zhu, Undergraduate Student, Statistics & Data Science, Iowa State University

Mentors:

Adisak Sukul, Associate Teaching Professor in the Department of Computer Science, Iowa State University

Shawn F. Dorius, Associate Professor of Sociology, Iowa State University

Stakeholder:

Iowa’s Cooperative Extension and Outreach Hotline Program

Program Support:

Madeline Johnson, Graduate Student, Statistics, Iowa State University

Technical Support:

Masoud Nosrati, Department of Computer Science, Iowa State University

Stakeholder: Iowa’s Cooperative Extension and Outreach Hotline Program

Project Website Video

25. Pilot a ‘Systems of Care’ Data Infrastructure to Support State Prevention, Treatment and Safety Response Efforts

Government programs often develop within agency silos, making it difficult to support ‘whole community’ responses to pressing problems. To combat this issue, the Iowa Linkage to Care Advisory Board was created to embrace cross-agency evidence-based policymaking in statewide prevention, treatment, and public safety response efforts. This project identified, webscraped, and spatially mapped publicly available data reflecting formal and informal ‘Systems of Care’ that support resilience related to mental health, physical health, education, workforce development, and child care. Interactive data tools and insights catalog and improve awareness of state resources in support of the Board’s ongoing efforts to address systemic change.

Fellows:

Kishor Kumar Sridhar, Graduate Student, Information Systems, Iowa State University

Interns:

Andrew Maloney, Recent Undergraduate/Incoming Master’s Student, Mathematics, Iowa State University

Joel Von Behren, Undergraduate Student, Data Science, Iowa State University

Matthew Voss, Recent Undergraduate/Upcoming Graduate Student, Statistics, Iowa State University

Mentors:

Heike Hofman, Professor and Interim Professor in Charge of the Data Science Program, Iowa State University

Shawn F. Dorius, Associate Professor of Sociology, Iowa State University

Stakeholders:

Iowa’s Linkage to Care Advisory Board in partnership with the Iowa Department of Public Health Substance Abuse Bureau

Technical Support:

Masoud Nosrati, Department of Computer Science, Iowa State University

Stakeholder: Iowa’s Linkage to Care Advisory Board with the Iowa Dept. of Public Health Substance Abuse Bureau

Project Website Video

26. Impacts of Dam Water Release Policy on Deschutes River Health and Recreation

The Deschutes River is a premiere rafting and flyfishing river, drawing both domestic and international visitors. In recent years water flow of the river has been altered because of changes in operation of the Pelton-Round Butte dam. This has led to a changes in water flow, water temperature, and water chemistry. We are conducting a retrospective analysis of the Deschutes river and its aquatic resources to inform local stakeholders as to the nature and causes of changes. From this may arise recommendations for water and natural resource management in this river system that experiences competing uses.

Fellows:

Sebastiano Busato, Oregon State University, Animal Science

Interns:

Sophia Bevans, Oregon State University, Biology/CIS minor

Duncan Gates, Oregon State University, Economics; Math/Pol Sci/Spanish minors

Mentors:

Scott Heppell, Associate Professor, Oregon State University

Stakeholder:

Lynn Ewing; City of Maupin; Deschutes River stakeholders; PG&E

Stakeholder: Lynn Ewing; City of Maupin; Deschutes River stakeholders; PG&E

Video

27. Forecasting Tools for Cost Analysis of Water and Wastewater Facilities in Oregon Small Towns and Cities

As small communities grow, they develop a need for centralized water and wastewater systems. Communities need cost analysis forecasting tools to help guide their choices in developing these systems. Working with the Oregon Association of Water Utilities, we are using recent data from the League of Oregon Cities plus additional data sources, we will identify key variables influencing facility capital and operating costs, and develop forecasting tools for cost analysis of water and wastewater facilities in Oregon’s small communities. We are doing a comprehensive assessment of costs including laying water mains, collection and distribution, and plant operation/construction.

Fellows:

Jakob Oetinger, Oregon State University, Statistics

Interns:

Amanda Reding Gott, Oregon State University, Natural Resources

Grayson White, Reed College, Mathematics Department

Mentors:

Christine Kelly, Professor, Oregon State University

Stakeholder:

Oregon Association of Water Utilities; Executive Director Jason Green

Stakeholder: Oregon Association of Water Utilities; Executive Director Jason Green

Video

28. Regulatory Impacts on Economic Development in the Eastern Oregon Border Region

Despite its proximity to Boise, Idaho, Malheur remains Oregon’s most impoverished county. The Eastern Oregon Border Economic Development Board is interested in comparing local (Malheur and Boise) and state (Oregon and Idaho) policies related to challenges in hiring people to fill jobs in Malheur, namely (1) regulations around professional licensure standards, (2) childcare options so parents can work and employers can fill their shifts, and (3) housing incentive program effectiveness. We are identifying and analyzing relevant data to identify where there is a mismatch in resources – skilled labor, childcare, and housing and options to alleviate these mismatches.

Fellows:

Thamanna Vasan, Oregon State University, Economics

Interns:

Melvin Ma, Oregon State University, Computer Science

Collin Robinson, Southern Oregon University, Computer Science

Mentors:

Stuart Reitz, Professor (Extension), Oregon State University

Stakeholder:

Eastern Oregon Border Economic Development Board (Economic Mobility)

Stakeholder: Eastern Oregon Border Economic Development Board (Economic Mobility)

Video

29. Wintertime Air Quality Health Impacts in Oakridge and Westfir

The communities of Oakridge and Westfir, Oregon, have consistently been among the worst 20 communities in the United States for air quality. Their health is compromised by soot from wood burning during the winter month, which leads to respiratory and cardiac challenges, disease, and cancer. We are using a variety of air quality and health data to statistically analyze and present results using data visualization and geospatial data analysis tools. The goal is to measure whether there are health impacts after significant smoke events and provide a baseline to measure improvements in health outcomes after implementing smoke mitigation measures.

Fellows:

Guen Patty, Oregon State University, Sustainable Forest Management

Interns:

Adam Conrad, Oregon State University, Computer Science

Pratiksha Aga, Oregon State University, Computer Science

Mentors:

Anne Thessen, Assistant Professor, Oregon State University

Stakeholders:

Sarah Altemus-Pope; Cities of Oakridge and Westfir

Stakeholder: Sarah Altemus-Pope; Cities of Oakridge and Westfir

Video

30. Water Quality Requirements for Fresh Produce Growers

This project is using publicly available water quality measurements from two different watersheds in Oregon to help both organizations (i.e. FDA and ODA) as well as individual farmers better understand the quality of water being used in fresh produce production. It is the goal of the project to help better inform the regulations being placed on farms while also providing farms with accessible information on their farm’s water source quality.

Fellows:

Heather Miller, Oregon State University, Mechanical Engineering, Minor in Public Health

Interns:

Zachary Boyce, Portland State University, Geography Major, Water Resources and GIS Minor

Gregory Gandy, Willamette University, Economics, Computer Science and Math Minors

Mentors:

Joy Waite-Cusic, Associate Professor, Oregon State University

Stakeholder:

Oregon Farms (OSU Extension); Oregon Dept of Agriculture (ODA) ; Food and Drug Administration – Center for Food Safety and Applied Nutrition; Produce growers in the Tualatin watershed and in Treasure Valley

Stakeholder: OR Farms, OR Dept. Agriculture, FDA, Growers in Tualatin and Treasure Valley

Video

31. Topic Classification for Citizen Complaints: A Case Study for Istanbul

In May 2020 only, Istanbul Metropolitan Municipality received almost a million complaints from the residents of Istanbul. By making a subject-based classification of written complaints addressed to the municipality, we aim to facilitate the communication of these complaints to the relevant Municipality Owned Enterprises (MOEs) in a shorter time. Hence, while the residents’ complaints will be addressed more quickly, the workers at the complaint desk will see the burden of their work reduced. Using online written complaints as our data source, we capitalize on NLP and ML algorithms for complaint processing and learning procedure. At the end, we obtain a tool that can predict the subject of any text and directs it to the right people.

Team members:

Meliha Gizem Çelik, Yıldız Technical University, MSc in Computer Engineering, 1st year

Neris Özen, Tilburg University, MSc in Data Science and Society, 1st year

Buğrahan Şentürk, Marmara University, BSc in Mechatronics Engineering, 4th year

Kubilay Gazioğlu, Yeditepe University, MSc in Data Science, 2nd year

Rana B. Kalkan, Sabancı University, BSc in Economics & Computer Engineering, 4th year

Ronahi Ay, Kırklareli University, BSc in Software Engineering, 3rd year

Stakeholder:

Kodluyoruz

İstanbul Büyükşehir

İstanbul Metropolitan Municipality

Stakeholder: İstanbul Metropolitan Municipality

Project Website Video

32. Social Distancing Detector

The purpose of this study is to develop an image processing/computer vision system which detects social distancing violations in Istanbul using data collected by security cameras provided by the municipality. After violations are detected, we visualize the violation volume density and hourly average distances at each location.

Team members:

Kubilay Gazioğlu, Yeditepe University, MS Candidate in Data Science, 2nd year

Rana Bengisu Kalkan, Sabancı University, BSc in Economics & Computer Engineering, 4th year

Meliha Gizem Çelik, Yıldız Technical University, MSc in Computer Engineering, 1st year

Stakeholder:

Kodluyoruz

İstanbul Büyükşehir

İstanbul Metropolitan Municipality

Stakeholder: İstanbul Metropolitan Municipality

Video

33. Wodensday: A Twitter Bot Predicting Density

Istanbul is one of the densest and most crowded cities around the world, which makes citizens’ lives challenging. It is difficult to navigate around the city since instant knowledge about what is happening where is currently not available. To overcome this challenge, we have developed a Twitter Bot that makes instant density prediction for specific locations around Istanbul, and informs the followers about the results.

Team members:

Ronahi Ay, University of Kirklareli, Software Engineering

Buğrahan Şentürk, Marmara University, Mechatronics Engineering

Mentors:

Engin Deniz Alpman, Bootcamp Trainer

Mehmet Fahri Bilici, Teaching Assistant

Stakeholders:

Kodluyoruz

İstanbul Büyükşehir

İstanbul Metropolitan Municipality

Stakeholder: İstanbul Metropolitan Municipality

Project Website Video