ACU Researcher

Dr Maryam Khanian Najafabadi

Senior Lecturer in Computer Science and Data Science
Australian Catholic University

Areas of expertise: natural language processing; sentiment analysis; recommender systems; graph neural networks; explainable ai; machine learning; deep learning; predictive analytics; educational data mining

Email: maryam.khaniannajafabadi@acu.edu.au

Location: ACU North Sydney Campus

HDR Supervisor accreditation status: HDR Supervisor (Full)

ORCID ID: https://orcid.org/0000-0002-5071-7515

Dr Maryam Khanian Najafabadi is a Senior Lecturer in Computer Science and Data Science at Australian Catholic University. She is a distinguished AI and Machine Learning researcher with more than nine years of academic and research experience across Malaysia, and Australia. Her teaching and research focus on natural language processing, recommender systems, and explainable AI, with a strong emphasis on ethical, transparent, and impactful AI for education, healthcare, and industry.

Maryam has coordinated and delivered large-scale courses in programming, data science, and AI at the University of Sydney (with over 800 students) and has led curriculum innovation to integrate Generative AI, explainable AI, and graph neural networks. At ACU, she contributes to program development and aligns teaching with the University's Responsible AI and Digital Trust research pillar, supervising both HDR and capstone projects.

Her research contributions include 20+ publications in top-tier Q1 journals (impact factors ranging from 2.8 to 9.588).

Maryam has received multiple research grants (FRGS, UTARRF, Research University Grants) and awards, including the Women Researcher Award in NLP and the Commendation for Excellence in Teaching.

Through her leadership in teaching, research, and community engagement, Maryam is committed to advancing responsible AI and mentoring the next generation of data scientists.

Website

Google Scholar / ORCID

Select publications

• Khanian Najafabadi, M. A Multi-Level Embedding Framework for Decoding Sarcasm Using Context, Emotion, and Sentiment Features (SAWE). Electronics, 2024.

• From theory to practice: The evolution and comparative analysis of homogeneous vs. heterogeneous GNNs in recommender systems. Neurocomputing, 2025.

• A systematic literature review on collaborative filtering techniques and implicit feedback. Artificial Intelligence Review, 2020.

• Improving the accuracy of collaborative filtering recommendations using clustering and association rules mining. Computers in Human Behavior, 2017.

• The state of the art and taxonomy of big data analytics: view from new big data framework. Artificial Intelligence Review, 2019.

Projects

Dr Maryam's current projects focus on advanced recommender systems and sentiment analysis, integrating deep learning, graph neural networks, and multimodal embeddings to address real-world challenges. Her projects include innovative frameworks such as:

• Multi-Aspect Sentiment, A next-generation aspect-based sentiment analysis framework for time-aware sentiment analysis.

• Embedded Self-Attention Transformer Recommender.

• Multi-Modal Semantic-Collaborative Graph Neural Networks for interpretable recommendations

• Personalized Career Pathways for Adolescents (Hybrid RS)

• SkinGPT-4 for Dermatology, Exploring multimodal LLMs to enhance dermatological diagnosis.

Awards

• Women Researcher Award in Natural Language Processing

• Commendation for Excellence in Teaching

• Top Instructor Award (high student engagement and feedback)

Public engagement

• Delivered AI workshops at Macquarie University and IEEE events

• Industry-academia collaborations in explainable AI and education

• Invited speaker at IEEE AI conferences and machine learning workshops