Sanda Harabagiu

Dr. Sanda Harabagiu is the Research Initiation Chair Professor in the Department of Computer Science at The University of Texas at Dallas (UTD), affiliated with the Erik Jonsson School of Engineering and Computer Science. Her expertise spans natural language processing, medical informatics, and artificial intelligence for public health. She holds dual doctorates in Computer Engineering (University of Southern California, 1997) and Electrical Engineering and Computer Science (University of Rome, 1994), alongside a diploma in Computer Science from the Polytechnic Institute of Bucharest (1983).

Her research focuses on advancing technologies for medical data analysis, including automatic extraction of actionable insights from radiology reports and EEG records. Notable projects include the Multimedia Vaccine Informatics System for analyzing social media discourse on vaccines and the development of AI tools for clinical decision support. She has led interdisciplinary collaborations through the Human Language Technology Research Institute (HLTRI), established in 2002 to pioneer advancements in human language processing.

Dr. Harabagiu’s honors include the 2019 AMIA Distinguished Paper Award and the 2017 Homer Warner Award. Her work bridges computational linguistics with healthcare, emphasizing applications in public health communication, misinformation detection, and clinical informatics. She has contributed to over 150 publications and served on numerous editorial and organizing committees for conferences such as ACL, AAAI, and AMIA.

• Education:
  • Ph.D., Computer Engineering, University of Southern California, 1997
  • Doctorate, Electrical Engineering and Computer Science, University of Rome, 1994
  • Diploma, Computer Science and Engineering, Polytechnic Institute of Bucharest, 1983
• Awards:
  • 2019 AMIA Distinguished Paper Award
  • 2017 Homer Warner Award
  • 2000 NSF CAREER Award
  • 1991-1993 Fondazione Ugo Bordoni Research Award

Her research also addresses social media analysis for public health, including frameworks to detect vaccine hesitancy and misinformation. Current projects involve leveraging large language models (LLMs) and multimodal data to understand communication patterns in health-related discourse. She has advised students like Travis Goodwin, contributing to impactful work in clinical informatics and AI ethics.