Characterizing dynamic functional connectivity subnetwork contributions in narrative classification with Shapley values

• Published in: Network neuroscience (Cambridge, Mass.) pp. 1 - 16
• Main Authors: Rossi, Aurora, Aeschlimann, Yanis, Natale, Emanuele, Deslauriers-Gauthier, Samuel, Dominey, Peter Ford
• Format: Journal Article
• Language: English
• Published: MIT Press 15.08.2025
• Subjects: Cognitive science; Machine Learning; Neuroscience; Statistics; Shapley values; fMRI; Temporal brain network; Narratives; Machine learning
• ISSN: 2472-1751; 2472-1751
• DOI: 10.1162/netn.a.25

Functional connectivity derived from functional magnetic resonance imaging (fMRI) data has been increasingly used to study brain activity. In this study, we model brain dynamic functional connectivity during narrative tasks as a temporal brain network and employ a machine learning model to classify in a supervised setting the modality (audio, movie), the content (airport, restaurant situations) of narratives, and both combined. Leveraging Shapley values, we analyze subnetwork contributions within Yeo parcellations (7- and 17-subnetworks) to explore their involvement in narrative modality and comprehension. This work represents the first application of this approach to functional aspects of the brain, validated by existing literature, and provides novel insights at the whole-brain level. Our findings suggest that schematic representations in narratives may not depend solely on preexisting knowledge of the top-down process to guide perception and understanding, but may also emerge from a bottom-up process driven by the temporal parietal subnetwork.