Research

We conduct methodological and empirical research in two directions:

  1. Leverage data science and AI as methodological tools to answer social science questions
  2. Examine benefits and harms of data science and AI for society

We actively work with under-resourced educational institutions and marginalized populations to help improve their conditions with data science and AI.

Current Projects

feature image

Longitudinal modeling of educational inequality

We investigate modeling strategies that convert longitudinal, unstructured data (e.g., digital traces, curricular content) into a rigorous understanding of how educational inequality accumulates through day-to-day teaching and learning experience.

feature image

Fairness and privacy in transfer learning

We examine issues of algorithmic fairness and data privacy in transfer learning to democratize access to trustworthy educational models especially for under-resourced contexts.

feature image

Digital divides in the age of generative AI

We leverage new data sources and analytical tools to track emerging digital divides incurred by the rapid development of generative AI at different levels of the educational system.