Loyola Marymount University Assistant Professor of Computer Science Lanyu Shang’s research focuses on developing investigative tools, models, and datasets employing human-centric AI, human-AI collaboration, social media analysis, AI for social good, and applied AI—all to address societal issues.
Human-centric AI refers to designing artificial intelligence systems that prioritize human needs, values, and ethical considerations, rather than focusing on results solely related to efficiency or automation. “I was drawn to teaching at LMU because my research is well aligned with one of the university’s key values of service to others through the application of knowledge to address social injustices and promote human dignity,” Shang said.
One of Shang’s recent co-authored publications presents a comprehensive social and news media dataset along with an analytical platform to facilitate research aimed at understanding the societal impact of drought. It’s common knowledge drought poses significant sustainability challenges, impacting agriculture, environments, ecosystems, public health, and socioeconomic stability. While studies have been conducted on the impact of drought using professionally measured data sources, people’s perspectives and sentiments about drought impact in the areas listed above remain largely underexplored.
To address this, Shang and collaborators developed SocialDrought, a novel and comprehensive dataset to facilitate further research on how people perceive the impact of drought both personally and for communities collectively. “My work aims to leverage social and news media to develop a more comprehensive understanding of drought’s societal impact,” Shang explained.
SocialDrought consists of three major components: 1) more than 1.5 million social media posts, 2) over 1,400 news articles collected and verified by domain experts, and 3) 31,000+ meteorological records from the U.S. Drought Monitor related to drought severity. In addition, the accompanying online analytical platform enables interactive and real-time data exploration to gain timely insights into the societal impacts of drought.
Shang’s second area of research is related to developing ways to capture and measure online discourse (via social media) related to the social impact of a major health crisis, such as the COVID-19 pandemic, as well as address ways to identify and debunk related health misinformation on social media. The threat of rapidly spreading health misinformation through social media during a crisis, such as a global pandemic, emphasizes the importance of addressing both clearly false information and complex misinformation, including conspiracy theories and subtle distortions.
One example is Shang’s collaborative paper, MMAdapt: A Knowledge-Guided Multi-Source Multi-Class Domain Adaptive Framework for Early Health Misinformation Detection. The proposed novel AI framework called MMAdapt can detect misinformation related to new and emerging health issues at an early stage. MMAdapt leverages resources from well-studied health areas, such as cancer and COVID-19, to identify misinformation in emergent health-related areas such as the 2022 Mpox outbreak. This AI framework can discern not only false claims, but also partially misleading content containing a mixture of accurate and inaccurate statements that can be convincing to the public. The goal is to enable timely interventions by agencies and decision-makers when new public health issues arise.
“Most of my research is motivated by real-world examples of inequities or challenges where these datasets and models facilitate research to aid decision makers in finding solutions that positively benefit affected communities,” said Shang. She currently has three LMU undergraduate students participating in her research and plans to engage more students in ongoing investigations.
Shang earned a Ph.D. in information science from the University of Illinois Urbana-Champaign. She received her master’s degree in data science from New York University and graduated cum laude with a bachelor’s degree in applied mathematics with specialization in computing from the University of California, Los Angeles.
