Portrait of Maria Cutumisu

Maria Cutumisu

Affiliate Member
Associate Professor, McGill University
Research Topics
AI and Healthcare
AI Ethics
Applied Machine Learning
Deep Learning
Generative Models
Large Language Models (LLM)
Machine Learning Theory
Natural Language Processing
Reinforcement Learning

Biography

Maria Cutumisu is an associate professor in Learning Sciences at the Department of Educational and Counselling Psychology, Faculty of Education, McGill University. Previously, she was a tenured Associate Professor in the Department of Educational Psychology, Faculty of Education, at the University of Alberta, where she established her lab in 2015 in the area of Measurement, Evaluation, and Data Science affiliated with the Centre for Research in Applied Measurement and Evaluation (CRAME). She is also an Adjunct Professor in the Department of Computing Science, Faculty of Science, University of Alberta. She graduated with an M.Sc. and a Ph.D. in Computing Science from the Department of Computing Science, University of Alberta and she trained as a postdoctoral scholar in Learning Sciences at the Stanford Graduate School of Education's AAA Lab.

Her research draws on computing science and educational psychology and has been funded by tri-council grants and scholarships as a principal investigator (NSERC DG, NSERC CGS-D, SSHRC IG, and SSHRC IDG) and as a co-principal investigator (SSHRC IG, SSHRC IDG, NSERC CREATE, and CIHR). Her research interests include feedback processing and memory (SSHRC IDG grants), machine learning and educational data mining for automated feedback generation (NSERC DG), game-based assessments that support learning and performance-based learning (SSHRC IG grants), computational thinking and data literacy (CanCode Callysto grants, CCTt tests, and SSHRC IG), AI in games (reinforcement learning in computer role-playing games) and non-player character (NPC) behaviours (NSERC CGS-D), and serious games (the RETAIN game for neonatal resuscitation; FRQS). She employs learning analytics to investigate the impact of K-16 student choices (e.g., willingness to seek critical feedback and to revise) and mindset on learning outcomes in an online game-based assessment to understand how prepared students are to learn and innovate. She uses psychophysiological technology (eye-tracking and electrodermal activity wearables) to provide a comprehensive understanding of student learning and memory processes (SSHRC IDG, Killam).

Publications

Predicting the Mathematics Literacy of Resilient Students from High‐performing Economies: A Machine Learning Approach
Yimei Zhang
Predictive Modeling of Body Image Dissatisfaction in People With Type 1 Diabetes
COURTNEY SOUTH
SHAHRYAR EBRAHIMI
A. Brazeau
Predictive Modeling of Body Image Dissatisfaction in People With Type 1 Diabetes
COURTNEY SOUTH
SHAHRYAR EBRAHIMI
ANNE-SOPHIE BRAZEAU
Predicting teachers’ research reading: A machine learning approach
Mehrdad Yousefpoori-Naeim
Surina He
Ying Cui
A Randomized Controlled Simulation Trial of a Neonatal Resuscitation Digital Game Simulator for Labour and Delivery Room Staff
Christiane Bilodeau
Georg M. Schmölzer
Using machine learning to predict student science achievement based on science curriculum type in TIMSS 2019
Yajie Song
Using machine learning to predict student science achievement based on science curriculum type in TIMSS 2019
Yajie Song
Cognitive, interpersonal, and intrapersonal deeper learning domains: A systematic review of computational thinking
Hao-Yue Jin
Assessing Numerical Analysis Performance with the Practi Mobile App
Kristin Garn
Raymond J. Spiteri
The Effects of a Digital Game Simulator versus a Traditional Intervention on Paramedics’ Neonatal Resuscitation Performance
Georg M. Schmölzer