Diyi is a PhD student at Language Technologies Institute, Carnegie Mellon University, advised by Prof. Robert Kraut and Prof. Eduard Hovy. Her research interests lie in Social Computing and Natural Language Processing. She received her bachelor degree from Shanghai Jiao Tong University.

Research Summary

With social interactions rapidly growing online, how to decode this conversational text to study human behaviors at a large scale becomes increasingly important. Diyi’s research focuses on utilizing such data to study new social problems and design new methods to better understand human behaviors, with the goal of facilitating human-human and human-computer interactions. Specifically, she works in three areas: (1) analyzing semantics for language understanding, such as identifying semantic structures behind humor and recognizing different types of social support; (2) extracting social roles that group members occupy and modeling how role collaboration affects teamwork success, and (3) facilitating social interaction by developing interventions, such as building recommender systems to match users with appropriate tasks and connect them with similar others in online communities.

For more information, please visit her website:

http://www.cs.cmu.edu/~diyiy/