Event

SEMINAR: AI-powered Actionable Insights from Educational Data

Speaker: Mehrnoush Mohammadi. This thesis explores how AI can be strategically leveraged to bridge the gap between complex, multi-sourced data and the delivery of timely, interpretable, and pedagogically effective interventions.

Speaker: Mehrnoush Mohammadi

12:30pm

14 May, 2025

CIRES Boardroom (L502, Level 5, Hawken Engineering Building 50)

https://uqz.zoom.us/my/khosravi



The CIRES Centre and School of EECS are hosting the following HDR Progress Review Confirmation Seminar:

AI-powered Actionable Insights and Interventions from Multi-Sourced Educational Data

Speaker: Mehrnoush Mohammadi
Host: Prof Gianluca Demartini

Abstract:

Today’s educational environments are saturated with diverse data streams capturing students’ cognitive, behavioral, emotional, and contextual learning processes. From digital interactions and assessment outcomes to physiological and environmental signals, these multi-sourced data hold great promise for building more responsive and effective learning systems. However, realizing the full potential of this information for meaningfully enhancing educational practice remains a significant challenge. This thesis explores how Artificial Intelligence (AI) can be strategically leveraged to bridge the gap between complex, multi-sourced data and the delivery of timely, interpretable, and pedagogically effective interventions.

To pursue this aim, the study first investigates the current landscape of AI in Multimodal Learning Analytics (MMLA), identifying key limitations and opportunities for advancing the field. It then explores how Multi-view Representation Learning (MvRL) can harness diverse data sources to generate richer and more interpretable insights by capturing and integrating complementary and context-rich perspectives of the learning process. Finally, the research examines how these insights can be transformed into scalable, efficient, and pedagogically effective interventions, ultimately bridging the gap between analytical potential and real-world educational impact.

Together, these contributions lay the groundwork for developing educational AI systems that are not only technically sophisticated, but also pedagogically impactful, scalable, and suited to the complexities of real-world learning environments.

Short Bio:

Mehrnoush Mohammadi is a Ph.D. candidate at the University of Queensland, Australia, affiliated with the School of Electrical Engineering and Computer Science and the CIRES Research Centre. She holds a bachelor’s degree in Computer Software Engineering and a master’s degree in Artificial Intelligence and Robotics from the University of Kurdistan, Iran. Her current research focuses on AI-powered actionable insights and interventions from multi-sourced educational data. She is supervised by Dr. Hassan Khosravi, Prof. Shazia Sadiq, and Prof. Wojtek Tomaszewski.

View all events