Associate Professor, Department of Data Science
Director, M.S. Data Science Program
New Jersey Institute of Technology (NJIT)
I am one of the founding faculty members of the Department of Data Science at NJIT and I direct the M.S. Data Science program.
My research interests lie at the intersection of information visualization and human-centered data science. I use visualization as a communication medium between data-driven computational models and human reasoning about information.
I direct NJIT's Intelligible Information Visualization Lab (NiiV), where we pursue intelligibility as the foundational principle for making information more accessible, meaningful, and actionable to experts (e.g., doctors, climate scientists) and non-experts alike.
Design and evaluate explanation methods and interactive visualization techniques for probing score-based and learned algorithmic rankers.
Provide domain experts and model developers with tools that explain the decisions of machine learning models and help them semantically validate models.
Adapt visualizations to prevent disclosure of sensitive information by developing information loss metrics that can help address the trade-off between privacy gain and loss of utility due to anonymization.
Let domain scientists reason about computational model behavior and help them select the most accurate models by interactively comparing multiple facets of model performance.
Conduct user studies with experts from biology and climate science domains to evaluate if and how optimal visualization design can overcome potential biases due to familiarity.
Study and survey of the visualization design space for devising classification schemes that bridge human perception with visual encodings.