UVM Earns $20M Research Grant to ‘Harness the Data Revolution’

Newswise — A groundbreaking data science effort to better understand and harness the power of stories has earned the University of Vermont a $20 million research capacity building award from the National Science Foundation (NSF) through its Established Program to Stimulate Competitive Research (EPSCoR). The five-year Research Infrastructure Improvement (RII) Track-1 award, which promotes world-class research nationwide, will bolster research infrastructure at UVM and across the state.

"Research is the lifeblood of our university, and the support we receive from programs such as this is crucial to driving our success,” said UVM President Suresh Garimella. “We are so grateful to the National Science Foundation and the EPSCoR program, which have been longtime allies in backing innovation and discovery that are vital to UVM’s mission as a top research institution.”

Harnessing the Data Revolution for Vermont: The Science of Online Corpora, Knowledge, and Stories (SOCKS) revolves around stories as an essential part of how people comprehend, explain, predict, and seek to navigate the world. SOCKS supports the Digital Humanities by developing a powerful approach to quantifying both individual stories and ecologies of stories through massive data collection, natural language processing, and large language models—computer-based encodings of the meaningful connections between words and phrases.

The cornerstone for SOCKS is StoryWrangler, a curation of Twitter into day-scale phrase counts for over 200 billion tweets in 100 languages from 2008 through to mid-2023. The massive sociolinguistic data set accounts for social amplification via retweets, which can be visualized through time series “contagiograms.” The instrument underlies UVM’s Hedonometer, a long running measurement of the happiness and sadness of populations. In 2022, The Economist used the instrument to quantify changes in Russian sentiment toward the war in Ukraine. It was also recently used to show, for example, that mentions of “mental health” have become 100 times more common today than a decade ago.

The SOCKS project is intended to enable or enhance the study of any large-scale temporal phenomena where people matter including culture, politics, economics, linguistics, public health, conflict, climate change, and data journalism.

"In astronomy and biology, the telescope and the microscope helped us describe phenomena far beyond our limitations, opening up vast new scientific realms,” said Vermont Complex Systems Center Director Peter Dodds. “With the SOCKS program, we’re working to do the same for stories by building and refining instruments that can ‘distantly read’ and make sense of enormous collections of texts, whether they be libraries of books, streaming social media, or Vermont folktales from the 1800s. We need to understand how stories evolve and spread, the effects stories have on populations, and with SOCKS, we will help grow a measurement-first science of stories.”

The RII Track-1 is a statewide effort to catalyze science, technology, engineering and mathematics (STEM) capacity in Vermont.  The EPSCoR SOCKS research focus dovetails with state and national priorities as it allows for broad outreach and enables opportunities for a wide and inclusive range of expertise that will provide opportunities to develop new knowledge and increased workforce development across the state.

“Vermont research institutions are at the forefront of data science and their work is instrumental to expanding our knowledge of the power of data to help us understand our world,” said Sen. Peter Welch (D-Vt.). “This grant from the National Science Foundation will provide critical support for the groundbreaking research happening at the University of Vermont and across the state. I’m grateful for NSF’s support for Vermont’s world class academic institutions, and I congratulate UVM on this transformational award.” 

The EPSCoR program is designed to fulfill the mandate of the NSF to promote scientific progress nationwide. Jurisdictions are eligible to participate in the NSF EPSCoR Research Infrastructure Improvement (RII) Program based on their level of total NSF support over their most recent five years.

Through this program, NSF facilitates the establishment of partnerships among academic institutions and organizations in governmental, non-profit, and commercial or industrial sectors that are designed to effect sustainable improvements in research and development infrastructure and capacity.

“Through EPSCoR, NSF catalyzes the development of research capabilities across the country, creating sustainable scientific infrastructure and communities of innovation,” said NSF director Sethuraman Panchanathan. “This year's EPSCoR awards will serve individual states and the country as a whole with critical research on wildfire management, resilience in the face of climate change, biomanufacturing and advanced biomedical devices, and data science in the service of all disciplines.”

RII Track-1 awards provide up to $20M total over five years to support research-driven improvements to physical, cyber infrastructure, and human capital development in topical areas selected by the EPSCoR steering committee as having the best potential to improve future R&D competitiveness. The project’s research and capacity-building activities must align with the specific research priorities identified in the submitting jurisdiction’s Science and Technology (S&T) Plan.

“This funding includes $1M to double the power of the state’s high-performance computing environment, supporting Computational Social Science research in 20 departments at UVM along with seven institutions in Vermont,” said Chris Danforth, Director of the Vermont Advanced Computing Center. “Building on our corporate partnerships with MassMutual and Google, we’re thrilled to be working with fellow Co-PIs Randall Harp and Juniper Lovato from the Computational Ethics Lab to ensure the project advances privacy practices in the application of data science, as well as the many other scientists at Vermont institutions who will contribute to this effort.”

This significant award catalyzes existing strengths in computational social science – at UVM and five baccalaureate institutions in Vermont with 34 faculty at Middlebury, Norwich, Vermont State University (VTSU), Champlain College, Saint Michael’s College – and organizations such as Vermont Works for Women, Vermont Professionals of Color Network and many others – all working as part of an integrated and multidisciplinary team.  A newly established Center for Workforce Development at VTSU will include training the next generation of students in complex systems and data science from grades 7–12 through the post-doctoral level and providing teacher training for computer and data science to secure the long-term future of VT’s tech industry and associated economy. 

The previous focus of the VT EPSCoR program catalyzed the very successful Basin Resilience to Extreme Events (BREE) in Lake Champlain project. BREE identified strategies for resilience in the social ecological system of the Lake Champlain Basin and led to the establishment of the CIROH (Cooperative Institute for Research to Operations in Hydrology) program.

“At its core, our NSF EPSCoR program provides an opportunity for a large and diverse number of researchers, stakeholders and private sector partners to come together with UVM and leverage our strengths to create new knowledge, and build capacity for increased educational, workforce, science, technology, engineering and mathematics opportunities aligned with Vermont’s state priorities,” said Kirk Dombrowski, UVM Vice President for Research and EPSCoR Director.