Gabriel Doyle, Ph.D.

Associate Professor

Gabriel Doyle is a computational psycholinguist who wants to understand why we talk the way we do His research combines mathematical models of communication with emerging big data sources, such as Twitter conversations and e-mail databases, to create new approaches for understanding how we structure our speech and writing. His work has shown that Twitter can be used to map dialects within the United States, that the amount of information provided in a tweet trades off with how exciting and unexpected of an event it discusses, and that employees who eventually stay at or leave a company use “we” differently in their work emails. He also builds models for child language, both for analyzing the shape of parent-child conversations and determining what linguistic structure children can infer from their parents’ speech.