About

I’m a researcher and data scientist working in natural language processing. I’m interested in modeling how people express their subjective experiences through text, especially in the contexts of healthcare and the humanities, usually in the setting of online communities. I rely on unsupervised machine learning methods, and I re-explore the evaluation of these methods when applied to small, topic-focused datasets.

My past work has examined how postpartum people frame their birth experiences, how people communicate their pain levels to physicians, and how the use of word embedding models require additional stability tests when used to measure biases.

I’m currently a PhD candidate in Information Science at Cornell University, where I’m advised by David Mimno. I have a master’s degree in Computational Linguistics from the University of Washington and have worked as a data scientist and research intern at places like Microsoft Research, Facebook Core Data Science, and Pacific Northwest National Laboratory.

Please check my personal website for more information!

Education

PhD (ongoing), Information Science, Cornell University

MS, Computational Linguistics, University of Washington

BA, Program of Liberal Studies, University of Notre Dame

Blog Posts

    Maria Antoniak

    Profile picture of Maria Antoniak

    @mariaantoniak

    Active 4 years, 5 months ago