Conversational Surveys

Traditional surveys have straight-jacket questions to be answered, thus restricting the information that can be gotten. Today, Ziang Xiao, a Postdoc Researcher in the FATE group at Microsoft Research Montréal, talks about conversational surveys, a type of survey that asks questions based on preceding answers. He discussed the benefits of conversational surveys and some of the challenges it poses.

Guest

Ziang Xiao: Ziang Xiao is a Postdoctoral Researcher in the Fairness, Accountability, Transparency, and Ethics group at Microsoft Research, Montreal. He will join the Computer Science department at Johns Hopkins University as an Assistant Professor in 2024. He received his Ph.D. in Computer Science and B.S. in Psychology and Statistics & Computer Science from the University of Illinois Urbana Champaign. Ziang Xiao's research is motivated by the fundamental question of understanding humans at scale, e.g., how could we conduct robust and generalizable studies about human behavior? His goal is to enhance human-AI interaction to expand our knowledge about ourselves. In his Ph. D work, he designed and built conversational agents to collect high-quality information through survey interviews. He also works on other exciting topics such as information exchange, model evaluation, social computing, and human cognitive skills. Broadly, his work lies in the intersection of human-computer interaction, natural language processing, and social and personality psychology.