Naeemul Hassan
University of Maryland
College of Information
Biography
Dr. Naeemul Hassan is an Associate Professor in the Philip Merrill College of Journalism at the University of Maryland, jointly appointed with the College of Information Studies (iSchool). His research lies at the intersection of computational journalism, data science, and artificial intelligence, focusing on combating misinformation and enhancing the transparency and efficiency of news production. Dr. Hassan’s work combines natural language processing, machine learning, and human-centered approaches to improve how information is produced, verified, and consumed.
SRP Project Title
AI for Quality Healthcare Information
NAIRR Project
Advancing Explainable LLM to Bridge the Knowledge-Practice Gap in Healthcare Communication
Topical Areas
Applied Computer Science; Artificial Intelligence and Intelligent Systems; Computer Science; Health Sciences; Informatics, Analytics and Information Science; Media and communications; Other Computer and Information Sciences; Other Medical Sciences; Statistics and Probability; Visualization and Human-Computer Systems
Abstract
This project investigates how large language models (LLMs) can help bridge the gap between scientific best practices and healthcare journalism. Research shows that news coverage of medical treatments often omits critical details such as harms, evidence quality, or alternatives leading to public misunderstanding and even harmful health decisions. While frameworks exist to assess the quality of healthcare news, they are labor-intensive and not scalable. Our project explores the potential of LLMs (e.g., GPT models, LLaMA) to automatically evaluate healthcare news articles against science-informed criteria, provide explainable feedback, and support journalists in improving reporting quality. We will test models on a curated dataset of 2,000 expert-annotated healthcare articles and extend the evaluation to larger datasets.
Desired Skills
The project blends computational journalism, natural language processing, and human-computer interaction to advance both AI explainability and its practical applications in healthcare communication. Relevant expertise- Interest in AI/LLMs, computational journalism, or healthcare communication Familiarity with Python, machine learning, or NLP libraries (e.g., Hugging Face, OpenAI API) Experience with data annotation, text analysis, or evaluation frameworks Curiosity about interdisciplinary research that combines computer science, journalism, and public health Strong analytical and communication skills, with an openness to learning across fields
Lightning Talk Title
Advancing Explainable LLM to Bridge the Knowledge-Practice Gap in Healthcare
Keywords
Artificial Intelligence; Large Language Model; Health Information; Natural Language Processing