About

I am an independent researcher based in Chicago, IL and a recent graduate of the University of Chicago’s master’s program for Digital Studies in Language, Culture, and History. I specialize in applications of AI/ML models for analyzing human communicative data and digital communities, in particular the content and metadata of creative texts, social media, and everyday conversation.

My previous work includes the creation of the first known large-scale corpus of online fiction dating from 2016-2025, which I studied in my Masters’ thesis “A Computational Analysis of the Style and Semiotics of AO3 Communities of Practice”. I have also spent four years contributing documentation and pioneering methods for the management and development of resources in the Weston Game Lab and the Hack Arts Lab at UChicago’s Media Arts, Data, and Design Center. In 2024 I worked with developers at Infosys’s headquarters in Bengaluru, India researching applications of open-source LLMs for usage in licensed chatbots.

I graduated from UChicago in 2024 with a bachelor’s degree in linguistics and computer science, which I have often combined to apply unique perspectives to understudied aspects of human culture and interaction. My initial training in sociolinguistics and machine learning is used extensively in my current work to document and study human social norms and interactions in digital contexts.

Check out my GitHub for a selection of interesting coding projects and tools I’ve made, including a framework for assessing AI institutional bias and tools for using the SBERT LLM to encode and categorize large digital texts!

I can be contacted via email at ayang5@uchicago.edu or by clicking the ‘Contact’ tab.

CURRENT PROJECTS

• Documenting the impact of late-2010s Chinese media fandoms on current Chinese soft power in a forthcoming ‘Pop Culture Fandoms Encyclopedia’
• Using LLMs to analyze the function of roleplaying in community comments on the Kill Six Billion Demons website
• Adding to the online fiction corpus