Computational Social Interaction Analysis for Better Online Communities

Abstract

We live in an era where many aspects of our daily activities are recorded as textual and activity data, from social media posts, to medical and financial records, to work activities captured by Wikipedia and other online tools. My research combines techniques in natural language processing and theories in social science to study human behavior in online communities, with the goal of developing new theories and interventions to improve or build sociotechnical systems.  In this talk, I will explain my research from two specific studies. The first one focuses on understanding how people collaborate to finish work by identifying social roles that they occupy in online production communities. The second part examines how people seek and offer support by modeling their support behaviors in online health support communities and quantifying how exchanging support affects their commitment. Through these two examples, I show how we can accurately and efficiently measure people's skills and needs to build collaborative and supportive online communities. 

Bio

Diyi Yang is a Ph.D. Candidate in the Language Technologies Institute at Carnegie Mellon University, advised by Prof. Robert Kraut and Prof. Eduard Hovy.  She received her bachelor degree in Computer Science from Shanghai Jiao Tong University, China. Her research bridges Social Computing and Natural Language Processing to understand and measure human behavior in large social systems and design new interventions to facilitate people’s online interaction. Her work has been published in leading NLP/HCI conferences. Diyi has been awarded Carnegie Mellon Presidential Fellowship and Facebook Ph.D. Fellowship.