Social Links
Contact
Greetings! My name is Lingyao Li.
I am an Assistant Professor at the University of South Florida, School of Information. Before joining USF, I completed my postdoctoral research at the University of Michigan's School of Information, where I worked with Dr. Libby Hemphill. I earned my Ph.D. in Civil and Environmental Engineering from the University of Maryland, College Park, advised by Dr. Gregory Baecher and co-advised by Dr. Michelle Bensi. I am also fortunate to have the chance to work closely with Dr. Yongfeng Zhang from Rutgers University.
During my Ph.D. study, I developed a strong passion for human-centered data science, leveraging crowdsourced data and natural language processing to tackle complex problems. To build a solid interdisciplinary foundation, I completed 25 courses covering civil engineering, statistics, information science, and computer science during my Ph.D. After my Ph.D. and a short Postdoc at the University of Maryland, I chose to spend two more years at the University of Michigan's School of Information to deepen my expertise in computational social science, social computing, and AI studies.
I consider myself an interdisciplinary researcher dedicated to integrating AI technologies with domain knowledge to address critical socio-technical challenges in the context of urban informatics and health informatics (AI for social good). Most of my studies explore the following key questions:
How can crowdsourced data be leveraged to analyze public perceptions and behaviors related to policies and events, thereby supporting critical decision-making process?
How can advanced AI techniques, such as large language models, be utilized to process human-generated content and develop conversational agents that deliver reliable and trustworthy recommendations?
How can crowdsourced data and AI technologies empower individuals to better interact with their environments and improve their online information-seeking experiences?
My research interests mainly include:
Natural Language Processing, Large Language Models
Social Networks, Crowdsourcing
Urban Informatics
Health Informatics
Below is my research landscape.
My research primarily leverages artificial intelligence (AI) techniques with crowdsourced data from social media and mobile phones, to address socio-technical challenges in two key areas: Urban Informatics and Health Informatics. In urban informatics, my work explores three layers of communities—resilient, equitable, and smart. My research explores the potential of “citizen-as-sensors” to gain insights into community resilience, disaster impact, public emotional and behavioral responses, and public perceptions of healthcare accessibility. In health informatics, my current research emphasizes two areas: (1) engaging with public opinions and experiences, both in response to therapeutic interventions and public health policies, and (2) empowering individuals with LLM-driven multi-agent systems or chatbots to facilitate health information-seeking or education.
My research agenda also explores topics in LLMs. These include (1) studying LLMs’ reasoning capabilities in logical, mathematical, and computational social science tasks and their trustworthiness in information retrieval, and (2) examining the societal and scientific impacts of LLMs across multiple sectors, including their impact on scientific communities through the lens of science-of-science. These pursuits form another crucial part of my ongoing research, which emphasizes responsible AI.
Ph.D. in Civil & Environmental Engineering, University of Maryland, College Park
M.S. in Naval Architecture & Ocean Engineering, Harbin Engineering University
B.S. in Naval Architecture & Ocean Engineering, Harbin Engineering University
Minor in Business Administration, Harbin Engineering University
2024 – Present: Assistant Professor, School of Information, University of South Florida
2022 – 2024: Postdoc, School of Information, University of Michigan
2022: Postdoc, Department of Civil & Environmental Engineering, University of Maryland
2017 – 2021: Graduate Assistant, Department of Civil & Environmental Engineering, University of Maryland
2012 – 2014: Graduate Assistant, Department of Naval Architecture & Ocean Engineering, Harbin Engineering University
2025
Jan. 2025. Our work "AIPatient: Simulating patients with EHRs and LLM powered agentic workflow" was accepted by AAAI 2025 workshop on Advancing LLM-based Multi-Agent Collaboration in Philadelphia, PA.
Jan. 2025. Our work "An Investigation of large language models in clinical triage: Promising capabilities, persistent racial and gender biases" was accepted by AAAI 2025 workshop on Generative AI for Health in Philadelphia, PA.
2024
Dec. 2024. Our work "Asessing Inequitable Social Responses to Wildfires: A Case Study of California Using the Epidemiology Model" was presented at oral session at AGU Fall Meeting 2025.
Dec. 2024. Our work "Assessing the damage of natural disasters using multimodal large language models and social media crowdsourcing" was presented at eLightening session at AGU Fall Meeting 2025.
Nov. 2024. Our work "AIPatient: Simulating patients with EHRs and LLM powered agentic workflow" was submitted to AAAI 2025 workshop on Advancing LLM-based Multi-Agent Collaboration at Philadelphia, PA. Thanks for Huizi Yu and Dr. Lizhou Fan's great lead and other collaborators' efforts.
Nov. 2024. Our work "An Investigation of large language models in clinical triage: Promising capabilities, persistent racial and gender biases" was submitted to AAAI 2025 workshop on Generative AI for Health at Philadelphia, PA. Thanks for Joseph Lee and Dr. Shu Yang's great lead and other collaborators' efforts.
Nov. 2024. Attended the ENNLP at Miami, FL. Our work "BattleAgent: Multi-modal dynamic emulation on historical battles to complement historical analysis" was presented at EMNLP Demo.
Oct. 2024. My proposal "Using crowdsourcing through online reviews and large language models to investigate public perception of healthcare facilities" collaborated with Dr. Siyuan Ma and Dr. Yongfeng Zhang was submmited to NVIDIA Data Science Track.