Dan Villarreal was recently awarded a Pitt Momentum Funds Seeding Grant for the project “Overlearning speaker race in sociolinguistic auto-coding”. This project extends Dan’s earlier research to develop a machine-learning algorithm that efficiently categorizes sociolinguistic data (such as whether a speaker uses “r-dropping” in a word like car). Dan will work with colleagues at Dartmouth College and a Pitt grad student to assess whether this algorithm performs equally well when processing the speech of Black and White speakers. This research will contribute to a growing body of knowledge in computational sociolinguistics about bias and equity in artificial intelligence.