Ziang Xiao joins the Johns Hopkins University as an assistant professor of computer science and a member of the Data Science and AI Institute.
Xiao completed his PhD in computer science at the University of Illinois Urbana-Champaign. Before joining Johns Hopkins, he was a postdoctoral researcher in the Fairness, Accountability, Transparency, and Ethics group at Microsoft Research Montréal.
Tell us a little bit about your research.
My work focuses on human-computer interaction, or HCI. With my background in both computer science and psychology, I am interested in how we can build technologies that can effectively work with humans and how these technologies affect us. Particularly, I want to investigate how we can use technology to understand human behavior at scale. Currently, my research has three primary pillars: 1) AI for social science, where I develop tools for social scientists to conduct robust and generalizable studies to understand human behavior; 2) human-centered AI evaluation, focusing on the techniques and frameworks to build rigorous and meaningful AI evaluations; and 3) information seeking, centered on understanding how people seek, consume, and produce information with various technologies.
Tell us about a project you are excited about.
Several of my projects aim to improve social science research methods using interactive systems such as conversational agents. For example, we are developing AI-powered conversational agents that can ask people questions and elicit meaningful information to understand people’s perspectives, experiences, and opinions. Although our study showed that a chatbot can effectively collect high-quality information from people and deliver an engaging experience, the quality of interview carried out by the agent is far inferior to those led by experienced human interviewers. Achieving comparable depth and nuance requires sophisticated conversational skills that may take a human interviewer years of training. So, how can we equip conversational agents with the skills of human interviewers? How do we facilitate social scientists to derive meaningful insights from such conversations at scale? And how can we ensure that privacy is protected while still enabling rich, meaningful conversations?
Why this? What drives your passion for your field?
Understanding human behavior is the key to designing better policy and interventions to improve our living conditions—however, we know very little about ourselves. When I was an undergrad studying social psychology, I found that a lot of great research ideas are difficult to operationalize. For example, it is challenging to collect rich and nuanced information from people in their daily contexts and to reach the population we care about; these challenges greatly hinder human understanding. Therefore, I see an opportunity to change how we understand human behavior at scale through novel technologies. The technologies we’re building have the potential of fundamentally changing the social science research paradigm by bridging quantitative and qualitative research methods. However, this transformation will require not only technical innovation but also careful studies on how people interact with those technologies. The aspiration to uncover deeper insights into how we think, feel, and act motivates my research.
What classes are you teaching?
I am teaching Introduction to Human-Computer Interaction in the fall and Advanced Human-Computer Interaction: Research Methods class in the spring. Both classes will focus on the human side of computer science. The first class is a project-based class in which the students will learn and practice human-centered design, and the second is for students who want to conduct research in HCI; we will have lectures on various research methods in HCI and discussions on critiquing classic and frontier research topics in the field.
Why are you excited to be joining the Johns Hopkins Department of Computer Science?
Johns Hopkins has a growing, diverse HCI community made up of people from a wide range of disciplines. Here, interdisciplinary research is deeply appreciated and valued; I find that my research is well-supported and that faculty members are collaborative and open-minded. I also enjoy speaking with faculty both inside and outside our department, and, most importantly, with our exceptional students, who are curious, enthusiastic, and inspiring. I’m excited to contribute to this community and collaborate across disciplines to grow the study of HCI at Hopkins.
Besides your work, what are some of your other hobbies and passions?
Outside of work, I like things that are more tangible. In graduate school, I was a darkroom technician at a local photography museum, but more recently, I’ve been getting into restoring old furniture and cars.