My research interests span topics in machine learning, signal processing, algorithmic bias/fairness, and data collection and annotations methods, especially as they pertain to human behavior and experience modeling. I am currently working on some exciting research identifying and characterizing the nature and severity of sources of gender bias in automated employee interviews, to address growing concerns regarding implicit machine learning bias. Recently, I worked on the IARPA-funded TILES research project, which aimed to find connections between physiologic, environmental, and contextual factors, and self-reports of mental states produced daily by professionals in and outside of the workplace. I also work on computational methods and tools for improving the accuracy of ground truth representations of human experiences gathered from continuous real-time annotations.
