Simon is a data scientist at NORC who specializes in analyzing large-scale digital data to answer public health research questions. His work blends machine learning, classification, and mixed-methods approaches to study health behaviors, commercial influences, and program effectiveness. Simon has experience working with unstructured data, such as social media posts, live stream chat data, and long-format interview transcripts. He translates these data into reproducible, policy-relevant insights. He is particularly focused on building transparent, scalable analytic pipelines that support broad research aims and projects.

At NORC, Simon has led data science efforts and supported projects examining tobacco and nicotine content across social media, including work funded by the National Institutes of Health related to smokeless tobacco products, flavored tobacco products, and e-cigarette prevention campaigns. He has developed machine learning classifiers and crafted experiment designs to support the study of youth exposure to commercial health messaging on social media platforms such as Twitter/X, TikTok, YouTube, Twitch, and more. Simon has also worked to assess how large language models could enhance qualitative coding, evaluation efficiency, and data validation workflows. His work emphasizes methodological rigor, transparency, and reproducible, responsible use of emerging AI tools.

Prior to joining NORC, Simon worked in the political science research space at the University of Michigan, where he supported research on voting behavior and measures of political nationalization. Across roles, Simon has consistently supported the development of new analytic approaches that support more efficient, effective research.