
My research interests focus on the application of advanced data science techniques, including machine learning, deep learning, artificial intelligence, and natural language processing, across interdisciplinary domains. In particular, I develop practical AI-driven solutions that support public health communication and address real-world information challenges. Building on a strong foundation in programming and data engineering, my work has increasingly centered on the use of generative AI and LLMs, including GPT, Gemini, Claude, Llama, and Mistral, for misinformation detection. I am especially interested in how these models can use external domain knowledge to improve the accuracy and reliability of health misinformation detection. More broadly, my goal is to contribute to the development of trustworthy, scalable, and domain-specific LLM-based models for digital platforms such as social media and search engines. These models can help such platforms detect, manage, and limit the spread of health misinformation while supporting users’ access to more trustworthy information.
Rostami, M., & Hawamdeh, S. (2025). Debunk Lists as External Knowledge Structures
for Health Misinformation Detection with Generative AI. Systems, 13(10), 882.
Rostami, M., Hossain, K. T., & Hawamdeh, S. (2025). Detecting Health Misinformation
by Leveraging LLM Models and Debunk List. In Proceedings of the ACM/IEEE International
Conference on Connected Health: Applications, Systems and Engineering Technologies
(pp. 341-346). Manhattan, New York.
Rostami, M., & Hossain, T. (2025). Diffusion of Health Information on Social Media-
A Research Review. In Proceedings of the 2025 Multidisciplinary Information Research
Symposium (MIRS). Denton, Texas, University of North Texas
Rostami, M., & Hossain, T. (2023). Health and Wellness Influencers' Role in COVID-19
Misinformation: Social Influence Perspective. In Proceedings of the 2023 Multidisciplinary
Information Research Symposium (MIRS). Denton, Texas, University of North Texas