Yuzhou Du

Yuzhou Du

Auto-generated profile, based on publicly available information

Yuzhou Du

Virginia Tech, Blacksburg, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 May 2024
Verified
Conference Paper
Open access
JCJohn Chen
John Chen
XLXi Lu
Xi Lu
YDYuzhou Du
Yuzhou Du
MRMichael Rejtig
Michael Rejtig
RBRuth Bagley
Ruth Bagley
UWUri Wilensky
Uri Wilensky
Large Language Models (LLMs) have the potential to fundamentally change the way people engage in computer programming. Agent-based modeling (ABM) has become ubiquitous in natural and social sciences and education, yet no prior studies have explored the potential of LLMs to assist it. We designed NetLogo Chat to support the learning and practice of NetLogo, a programming language for ABM. To understand how users perceive, use, and need LLM-based interfaces, we interviewed 30 participants from global academia, industry, and graduate schools. Experts reported more perceived benefits than novices and were more inclined to adopt LLMs in their workflow. We found significant differences between experts and novices in their perceptions, behaviors, and needs for human-AI collaboration. We surfaced a knowledge gap between experts and novices as a possible reason for the benefit gap. We identified guidance, personalization, and integration as major needs for LLM-based interfaces to support the programming of ABM.

5 August 2026 in Proceedings of the Human Factors and Ergonomics Society Annual Meeting
Verified
Journal Article
Closed access
DDDavid Du
David Du
SMSarah McGowan
Sarah McGowan
SDSara Do
Sara Do
OOOlumide A. Ojeifo
Olumide A. Ojeifo
JIJames Ivory
James Ivory
Nathan LauNathan Lau
Nathan Lau
Emergency department (ED) waiting rooms have complex soundscapes where nurses sometimes perform triage and documentation amid task-irrelevant sounds. This study examined whether auditory distraction affects documentation accuracy across noise types and interval patterns. Thirty-two ED nurses completed simulated triage in the Tesseract, an immersive multimodal simulation environment, across four Noise Types (alarms, infant crying, conversations, quiet baseline) and two Noise Intervals (continuous or intermittent). A behaviorally anchored error-coding framework with strong interrater reliability was used to assess severity-weighted documentation errors and free-text entry error counts. Noise conditions produced no significant effects on cumulative severity-weighted errors over quiet baseline. Free-text entry errors showed a significant Noise Type × Noise Interval interaction effect, χ 2 (2) = 12.92, p = .002. Conversations produced the highest error counts under continuous and infant crying under intermittent noise interval. Findings suggest noise-related errors can be dependent on the momentary soundscape, and documentation processes are vulnerable to disruption.