Natalie Ahn

I am a data scientist and computational social scientist. Currently, I am a lecturer at UC Berkeley's School of Information, teaching machine learning and natural language processing courses to students in the Masters in Data Science (MIDS) program. From 2019 to 2021, I lead the content data science team at Nextdoor. Before that, I was head of data science and machine learning at Hoodline / Pixel Labs, which was acquired by Nextdoor. I received my PhD in public policy from UC Berkeley, where I used natural language processing, machine learning, and quantitative analysis to study changes to government authority and how those changes related to leaders' fates after leaving office. I previously worked in journalism and foreign policy, focusing on international conflict, political-military coordination and post-conflict reconstruction in Iraq.

Research

• "Expansions of Executive Authority: Government Leaders' Near-Term Pressures and Long-Term Fates."
  PhD Dissertation, Goldman School of Public Policy, University of California, Berkeley. 2018. [Paper]


• "Inducing Event Types and Roles in Reverse: Using Function to Discover Theme."
  Proceedings of the Workshop on Events and Stories in the News, Association for Computational Linguistics (ACL). 2017. [Paper]


• "Comparing NLP Methods for Identifying Policy Decisions in Government Documents."
  Paper presented at the 2017 PoliInformatics Workshop. 2017. [Paper]


• "Rule-Based Spanish Morphological Analyzer Built From Spell Checking Lexicon."
  arXiv preprint, arXiv: 1707.07331 [cs.CL]. 2017. [Paper] [Code]


• "Measuring Consolidation of Power: Extracting Event Data from Laws and Decrees."
  Paper presented at the Annual Meeting of the American Political Science Association (APSA). 2016. [Paper]

CV, etc.

• CV


• Github


• LinkedIn

(If you’re looking for Dr. Natalie G. Ahn, Professor of Chemistry and Biochemistry at the University of Colorado - Boulder, see this site.)