SUDS Project:

Combining Natural Language Processing with Functional MRI to Understand the Imaginative Brain

Research description:

Our research focuses on the neural underpinnings of imagining future events. This ability relies on complex knowledge structures called schemas – knowledge about the world that scaffolds imagination. We recently developed a natural language processing (NLP) metric that assesses the schematicity of narratives describing imagined events. We now plan to combine this NLP tool with fMRI collected while participants describe aloud their imagined events.

The student on this project will have the opportunity to work with multi-echo MRI data that, when combined with advanced denoising techniques to remove motion artifacts resulting from speaking, enable more sensitive detection of BOLD (blood oxygen level dependent) signal. Processed fMRI timeseries data will be analyzed in conjunction with NLP timeseries data to determine whether the production of highly schematic narrative content modulates activity in brain regions thought to underpin schema, such as medial prefrontal cortex.

The SUDS Scholar will have the opportunity to work with experts in cognitive neuroscience, biomedical imaging and NLP, and will become familiar with neuroimaging methods as well as best practices in neuroinformatics and open science. The analytic approach for combining NLP and fMRI will provide a platform for future neuroscience research on the imaginative brain.

Year: 2026

Researcher:
Donna Rose Addis, Baycrest

Student:
Asha Tafarodi, McGill University

Through SUDS, undergraduate students engage in hands-on research focused on data sciences and AI methodology applications.