Published multiple papers, including 'Propensity-independent Bias Recovery in Offline Learning-to-rank Systems' (SIGIR 2021) and 'Understanding the Dynamics between Vaping and Cannabis Legalization Using Twitter Opinions' (ICWSM 2021). Received NSF CAREER Award to study Relational Causal Inference; her lab also received an Adobe Research grant to study heterogeneous treatment effect estimation.
Research Experience
Conducted research across various fields such as personalization, social media, social networks, psychology, journalism, and e-commerce. Presented talks at places like Facebook's Computational Social Science group and co-organized events such as the Women's Mentoring Session @ AAAI 2021.
Background
Associate Professor in Computer Science at University of Illinois at Chicago. Her research spans different aspects of data science, including machine learning, causal inference, graph mining, network science, and privacy. The goal is to unify these aspects into a single framework that allows for better reasoning with data and solving important societal problems. She is especially interested in algorithms for heterogeneous graphs and networks, focusing on identifying and resolving barriers to causal inference from relational data, improving machine learning models by addressing inherent biases in (found) data, and empowering people in their privacy choices through personalized privacy assistants.