In 2024, Data and Society Research Group was founded to provide actionable and data-driven insights for our society in addressing grand challenges including climate change, energy resilience, and human health outcomes. Our work involves developing data systems that seamlessly integrate automated text analysis, image recognition, and interactive geospatial data visualization. We also conduct in-depth interviews and surveys to capture the rich, contextual, and cultural nuances of the societal issues people face.
We combine modern tools with proven methodologies to deliver practical solutions that foster positive and meaningful change in communities and society.
We are dedicated to upholding the highest standards of ethical research, ensuring that our work is conducted with transparency, integrity, and a commitment to the responsible use of data.
We are committed to generating insights through rigorous data analysis, leveraging recent methodological developments to inform decision-making and address pressing social challenges.
We prioritize collaborative partnerships, working with diverse private, nonprofit, and public entities to co-create solutions that incorporate diverse perspectives, focusing on real-world problems.
Selected Research Projects
We have developed methodologies and datasets to measure public sentiment on solar energy in the United States using millions of social media data points. Our interactive map offers 10 years of data on city- and state-level sentiment on solar energy for over 3,500 cities across the country, with a balanced panel of 587 cities.
We are investigating how improving the exchange of energy and information between electric vehicles (EVs) and the electric grid can benefit people. So far, we have built a machine learning algorithm for V2B systems to save building users more energy by using one-day-ahead energy use prediction by 15 minutes.
We have developed a methodology and dataset for measuring household-level rooftop solar adoption rates in Colorado, USA, using an effective collection and processing of 1 million aerial images. Our predictive model achieves over 70% explained variance in explaining the proportion of roof areas covered by rooftop solar panels.
Institutional ecosystem mapping refers to a class of tools and methods for understanding the institutional structure and dynamics associated with complex policy domains. In collaboration with The Fire Chasers, we are co-creating datasets and an interactive web-based application to visually represent the diversity and scope of our current and potential partners. Our goal is to develop an environmental justice-based database and systems that will guide current and future investments and collaboratives.
Our Students and Researchers
MS, Computer Science. NC State.
Shaival is a full-stack developer working on technology-driven sustainability solutions. He completed his Masters in Computer Science in 2024, with a focus on artificial intelligence and data technologies. Prior to his Master's, he worked as a Machine Learning Engineer, where he gained extensive experience in predictive modeling, natural language processing, and back-end engineering.
PhD Student, Public Administration. NC State.
Jen is a consultant specializing in applied research, data analytics, strategy, and operations. She has held executive leadership roles in early-stage start-ups and large companies including Google (formerly DoubleClick), NBC Universal, and InMobi. Jen earned her MBA in Information Systems and Marketing from NYU Stern School of Business and BS in Applied Economics and Business Management from Cornell University.
Our Affliated Researchers
PhD Candidate, Public Affairs. CU Denver.
Crystal is a doctoral candidate and research assistant with the University of Colorado Denver. Her research focuses on energy policy with focus on energy equity, environmental justice, and the impact of perceptions of energy resources on the impact of societal values and perceptions of energy resources on energy policy.
PhD Candidate, Information Systems. CU Boulder.
Lan is a Ph.D. Candidate in Information Systems at Leeds School of Business, University of Colorado Boulder. Her research focuses on social media analysis, large language model (LLM) and IS Healthcare. Prior to joining Leeds, Lan earned her master's degree in computational linguistics from CU Boulder.