The world around us is teeming with information. This information is collected, organized, and integrated both by individuals trying to make sense of their world and by groups trying to make sense together. This process of sensemaking sits at the center of my research. Using interdisciplinary theories and methods applied to diverse sets of behavioral experiments and large-scale datasets my work explores information search, appraisal, and transmission among individuals.

The traditional way of gaining insights into group sensemaking leverages people’s behavior and judgments, observes their choices, and manipulates available information. My research complements this approach by integrating frontier language models into standard experimental paradigms. By combining modern natural language processing techniques with core theory and methods from the cognitive and decision sciences, my work demonstrates how new types of computational approaches can offer novel insights into how people are collecting, organizing, and integrating information.

In my postdoctoral work as a research fellow at the U.S. Army Research Institute, I am combining classic cognitive and industrial/organizational psychology ideas about group communication with tools from machine learning to address broad notions of team performance. One goal of this work is to build better models of team composition -- I am developing models of communication to understand how individual traits impact communication behavior and applying these models, along with an understanding of social dynamics, to build effective teams.