You never forget cold weather after living in South Bend for two years :)

I am a Postdoctoral Research Associate at the University of Virginia School of Data Science. My research develops and evaluates machine-learning methods for understanding complex human, social, and clinical data, with current work on medical foundation models, Vision-Language Models (VLMs), clinical feature grounding, and model interpretability in dermatology.

Broadly, my work sits at the intersection of machine learning, natural language processing, computational social science, and human-centered decision support. I am especially interested in academic roles where I can combine methodological AI research with interdisciplinary applications in health, social systems, and decision-making.

I earned my Ph.D. in Systems & Information Engineering from the University of Virginia. My dissertation, Enhancing Emotion Understanding in Messaging Interactions, integrated transformer-based language models with Affect Control Theory to study emotion, sentiment, and social meaning in online communication. This work led to a journal article in Sociological Methodology on contextual embeddings in sociological research.

Before my current postdoctoral role, I served as an Investment Officer at the Virginia Retirement System, where I applied machine learning, statistical modeling, and large-scale data analysis to mortgage-backed securities and fixed-income research. Across my academic and applied work, I have collaborated with researchers in data science, sociology, engineering, business, political science, nursing, kinesiology, economics, and medicine.

Research Interests

• Trustworthy and interpretable AI: medical foundation models, VLMs, model reliability, and clinical feature grounding.
• NLP and computational social science: contextual embeddings, sentiment analysis, emotion understanding, and social meaning.
• Applied machine learning: large-scale data analysis for decision support in health, finance, safety, and social systems.
• Human-centered systems: technology-enabled interventions, telematics, wearable sensing, and feedback systems.

Selected Work

• Contextual embeddings in sociological research. Developed methods for expanding the analysis of sentiment and social dynamics using contextual language models. Published in Sociological Methodology, 2024. Read paper.
• Medical foundation models and dermatology VLMs. Current postdoctoral research on interpretability, clinical feature grounding, and reliability of vision-language models in dermatology.
• Sensor-free microclimate monitoring. Collaborated on work using LoRaWAN signal characteristics for environmental sensing and smart-city applications.
• Human-centered safety and decision-support systems. Contributed to projects on telematics-based fleet safety, RFID and haptics for collision prediction, and technology-enabled health research.

Updates