Announcing Summer 2025 Research at MDI

The Massive Data Institute at the McCourt School of Public Policy welcomes the Summer 2025 Cohort of student researchers participating in the MDI Scholars Program, the REU program, the Sonneborn program, and independent research endeavors. 

Conducting research alongside Georgetown Faculty, the nearly 30 Georgetown undergraduate and graduate students represent four colleges across Georgetown University, including the McCourt School of Public Policy, Walsh School of Foreign Service, Graduate School of Arts & Sciences, and the College, as well as 12 student researchers from other universities joining us this summer.

Over the summer, student researchers are working on research projects on topics ranging from AI generated art, healthcare, to election dynamics. 

While some students are participating in the MDI Scholars Program, we also have students working on other research projects with faculty affiliated with MDI.

Summer 2025 Research Teams

(listed in alphabetical order of advisor)

Using Big Data to Better Inform our Understanding of Forced Migration

Advisors: Ali Arab, Ph.D., Associate Professor in the Department of Mathematics and Statistics, Sonneborn Chair for Interdisciplinary Collaboration; Lisa Singh, Ph.D., MDI Director, Chair of the Department of Computer Science, Professor in the Department of Computer Science and McCourt School of Public Policy, Sonneborn Chair for Interdisciplinary Collaboration; Katherine Donato, Ph.D., Donald G. Herzberg Professor of International Migration, Sonneborn Chair for Interdisciplinary Collaboration
Description: The goal of the project is to use a unique combination of administrative, organic (social media, Google trends, newspapers, etc.), and survey data to improve our understanding of international migration. This includes developing machine learning and statistical modeling tools and measures from different data sources. 
Student Researcher(s): Izzy Coddington ’26, Master of Science in Mathematics and Statistics;  Haiqa Sarosh Fatima, Fall ’25, Master of Arts in Migration Analytics; Adrian David Frauca ’27, Bachelor of Science in Computer Science; Oliver Hannagan ’26, University of Wisconsin, Madison 

Understanding the Role of Social Media for Migrant-Host Relations in Colombia

Advisor: Nejla Asimovic, Ph.D., Assistant Professor in Computational Social Science, McCourt School of Public Policy
Description: In this project, we aim to characterize the narratives surrounding migration in Colombia as reflected in news outlets and social media platforms, using online data collection and text analysis. We will also explore how various social media platforms are used and how they shape the experiences of Venezuelan migrants in Colombia, with particular attention to their sense of belonging and social capital.
Student Researcher(s): Stacy Che ’26, Master of Science in Data Science and Analytics; Gabriella Cova ’26, Master of Public Policy

Digital Approach to Spotlighting Common Ground Across Group Divides

Advisor: Nejla Asimovic, Ph.D., Assistant Professor in Computational Social Science, McCourt School of Public Policy
Description: This project involves developing and testing a digital tool designed to identify and enhance the visibility of points of cross-group consensus. A two-week experiment will compare the effects of conversing in an environment guided by two algorithms: one prioritizing messages with high cross-group agreement and the other using chronological ranking. The study, funded by the Tech and Public Policy grant, will be implemented in collaboration with an online dialogue platform that connects individuals across political divides.
Student Researcher(s): Stacy Che ’26, Master of Science in Data Science and Analytics; Gabriella Cova ’26, Master of Public Policy

Investigating the Characterization of Healthcare-Seeking Behavior and Disease Transmission from Mobility Data: Balancing Public Health Needs and Privacy Issues

Advisor(s): Shweta Bansal, Ph.D., Professor of Biology and Giulia Pullano, Ph.D., Fritz Fellow & Postdoctoral Associate
Description: This project examines the balance between utilizing high-resolution mobility data for public health purposes and addressing privacy concerns related to identifying sensitive healthcare-seeking behavior and characterizing disease transmission. To achieve this, we will apply privacy-preserving techniques to mobility data and assess the effectiveness of private versus non-private mobility data in generating public health insights and guiding interventions.
Student Researcher(s): Muhammad Saad ’26, Data Science for Public Policy

Describing US Voting Preferences using Partial Differential Equations

Advisor: Bogdan Raita, Ph.D., Assistant Professor in Department of Mathematics and Statistics
Description: We model voting preferences in a two-party system using the Fokker–Planck equation. This is a partial differential equation modeling how opinions in a population evolve over time. We use AI tools to solve the equation numerically using artificial data.
Student Researcher(s): Katherine Arkin ’26, Bachelor of Science in Mathematics, Computer Science Minor; Xin Li, Doctoral Student in Applied Mathematics 

The Election Officials’ Communications Tracker

Advisor(s) / Collaborators: Thessalia Merivaki, Ph.D., Associate Teaching Professor, McCourt School of Public Policy, and Associate Research Professor, Massive Data Institute; Mara Suttmann-Lea (Connecticut College); and Algorithmic Transparency Institute (ATI.io)
Description: This project aims to identify communication strategies election officials use online to inform the public about how to participate in elections, and build trust in the electoral process. Using manual quantitative coding methods and automated encoding procedures using LLMs, we monitor and label communications shared by state and local election officials on social media.
Student Researcher(s): Aditya Vishahan ’26, Bachelor of Arts in Government and Economics Minor; Matt Steinberg ’26, Master of Public Policy

Redesigning Democracy Research on Election Systems and Reform

Advisor: Thessalia Merivaki, Ph.D., Associate Teaching Professor, McCourt School of Public Policy, and Associate Research Professor, Massive Data Institute
Description: This project is done in partnership with the Center for Election Science (CES). McCourt students are paired with CES researchers to develop evidence-based policy recommendations for practitioners in the elections field.  Students are conducting research on youth voter participation and support for various election reforms, including approval voting.
Student Researcher(s): Ryann Alonso ’26, Master of Public Policy; Aliza Lifshitz ’26, Master of Public Policy 

Building robust algorithmic tools to advance the study of information integrity in digital ecosystems

Advisor(s) / Collaborators: Thessalia Merivaki, Ph.D., Associate Teaching Professor, McCourt School of Public Policy, and Associate Research Professor, Massive Data Institute; Renée DiResta, Associate Research Professor with the Massive Data Institute and Tech & Public Policy at the McCourt School of Public Policy;  Ioannis Ziogas, Ph.D., Assistant Teaching Professor at the McCourt School of Public Policy and Assistant Research Professor at MDI; and Algorithmic Transparency Institute (ATI.io)
Description: This project aims to improve social media data collection infrastructures to facilitate research on information integrity in the fields of public health, energy management, and election administration.
Student Researcher(s): Ibadat Jarg ’26, Data Science for Public Policy

Guiding Educators on Sharing and Protecting Student Data through Privacy Enhancing Technologies

Advisors: Amy O’Hara, Ph.D., Research Professor at MDI and Executive Director of the Georgetown Federal Statistical Research Data Center at the McCourt School for Public Policy; Stephanie Straus, M.Ed., Policy Fellow at MDI
Description: Privacy Enhancing Technologies (PETs) allow for increased data sharing and access while simultaneously preserving the utility and privacy of that data. MDI is assisting state and local education agencies in implementing PET pilots that fill a data gap in their student longitudinal data systems. In addition to these pilots, MDI has created a website of resources for education data owners that includes a bibliography on existing PETs, real-world examples, and a PET 101 training series. https://mdi.georgetown.edu/privacy-enhancing-technologies
Student Researcher(s): Victor Chen ’27, Bachelor of Science in Computer Science; Yiming Wu ’26, Master of Public Policy

Georgetown Equitable Data Access Project/Maintaining and Improving National Data Infrastructure 

Advisor: Amy O’Hara, Ph.D., Research Professor at MDI and Executive Director of the Georgetown Federal Statistical Research Data Center at the McCourt School for Public Policy
Description: The Georgetown Equitable Data Access Project will streamline data discovery and access for researchers, and improve researcher capacity to use administrative data through the Georgetown University Research Data Center (GURDC). The GURDC is one of 35 secure federal statistical data centers across the country which grant approved researchers access to a rich array of non-public data. We aim to help train a diverse group of analysts in applying innovative methods to assess data quality and bias in administrative and linked data from the GURDC. In addition, students will research active and potential disruptions to federal data systems and assess the impact on measures of the U.S. economy and population.
Student Researcher(s): Claire Wootton ’26, Master of Public Policy; Alicia Gopal, Fall ’25, Bachelor of Arts in Economics and Statistics

Investigating Cross-Country Effects of Discrepancies Between Self-Reported and Behavioral Effort on Student Performance

Advisors: Qiwei Britt He, Ph.D., Provost’s Distinguished Associate Professor, Data Science and Analytics Program, Georgetown University; David Pepper, Ph.D., Senior Lecturer, International Education and Educational Assessment, King’s College London, United Kingdom
Description: Self-reported effort may not always align with actual behavioral effort and performance. Over- or underestimation can be influenced by cultural background, potentially introducing biases in students’ self-efficacy scale and, consequently, affecting their test performance. This study examines the gap between self-reported and actual behavioral effort, analyzing its impact on test performance using the differential item functioning approach within the framework of item response theory, while considering country and gender effects.
Student Researcher(s): Yuxi Shen ’26, Master of Science in Data Science and Analytics

Experiential Research into Perceptions of Ownership over AI Generated Art

Advisors: Toni-Lee Sangastiano, Ph.D., Digital Media Specialist and Associate Professor of the Practice in the Department of Art & Art History, and Medical Humanities Core Faculty; Kristelia García, J.D., Anne Fleming Research Professor of Law, Institute for Technology, Law & Policy; Elissa Redmiles, Ph.D., Clare Luce Boothe Assistant Professor in the Department of Computer 
Description: How do lay people perceive AI-generated artistic outputs with regards to authorship and the protection of AI-generated art? In order to collect perception data that can inform future legislation regarding public and stakeholder opinion. Specifically, we are analyzing the results of a series of experiential research experiments in the form of juried art competitions in order to gain a robust socio-technical understanding of authorship, incentives, and values.
Student Researcher(s): Hexuan “Judy” Wang ’27, Bachelor of Art in Political Economics and Art 

Policy2Code

Advisor(s): Lisa Singh, Ph.D., MDI Director, Chair of the Department of Computer Science, Professor in the Department of Computer Science and McCourt School of Public Policy, Sonneborn Chair for Interdisciplinary Collaboration; Ariel Kennan, Senior Director, Digital Benefits Network, Beeck Center for Social Impact + Innovation
Description: Students will test how generative artificial intelligence (AI) technology can be used to translate government policies for U.S. public benefits programs into plain language and software code. These students aim to explore ways in which generative AI tools such as Large Language Models (LLMs) can help make policy implementation more efficient by converting policies into plain language logic models and software code under an approach known worldwide as Rules as Code (RaC).
Student Researcher(s) / Collaborator(s): Sophia Dorr ’27, Bachelor of Arts in Computer Science and American Musical Culture, and Mathematics Minor; Alessandra Garcia Guevara  ’26, Bachelor of Science in Computer Science; Avand Lakmazaheri ’26, Master of Arts in Communication, Culture & Technology; Ann Lian ’25 (Data Science for Public Policy), MDI Impact Scholar

AI Readiness

Advisors: Lisa Singh, Ph.D., MDI Director, Chair of the Department of Computer Science, Professor in the Department of Computer Science and McCourt School of Public Policy, Sonneborn Chair for Interdisciplinary Collaboration
Description: Project description forthcoming!
Student Researcher(s): Zezhi “Henry” Deng ’26, Bachelor of Science in Computer Science and Mathematics, and Economics Minor; Saanvi Shashikiran ’27 Bachelor of Science in Computer Science, Bachelor of Arts in Psychology, Mathematics Minor

Firearms Policy Research

Advisors: Lisa Singh, Ph.D., MDI Director, Chair of the Department of Computer Science, Professor in the Department of Computer Science and McCourt School of Public Policy, Sonneborn Chair for Interdisciplinary Collaboration; Shweta Bansal, Ph.D., Professor of Biology; Sarah Adel Bargal, Ph.D., Assistant Professor of Computer Science and Provost’s Distinguished Faculty Fellow; Carole Roan Gresenz, Ph.D., Professor of Management and Policy and Professor of Public Policy
Description: This cohort of students will focus on modeling opinion as it relates to different firearm-related policies and events of the day. It is possible to work on stance detection using social media posts (Kawintiranon & Singh, 2021), and with the recent advancements in generative AI, this type of detection may be less costly with respect to manual data labeling. Therefore, this cohort will use a combination of generated training data, relevant public document data, and auxiliary data to improve opinion detection without labeling more data. Example auxiliary sources include public reviews, images, and network knowledge.
Student Researcher(s): REU Research Team

Additional Project Descriptions forthcoming!