Related Experiment Video
Updated: Aug 15, 2026
05:38
Interaction between Phonological and Semantic Processes in Visual Word Recognition using Electrophysiology
Published on: June 29, 2021
EEG-based classification models reveal differential neural processing of words and images
Neda R Morakabati1, Alison S Thiha1, Eitan Schechtman1
1Department of Neurobiology and Behavior and Center for the Neurobiology of Learning and Memory, University of California, Irvine, Irvine, California, USA, 92697.
Journal of Neuroscience Methods
|August 13, 2026
Summary
Machine learning decodes object categories from electroencephalography (EEG) data. Image trials show higher accuracy than word trials, highlighting EEG
Area of Science:
- Neuroscience
- Cognitive Science
- Machine Learning
Background:
- Machine learning with neuroimaging data monitors neural representations.
- These methods can differentiate brain networks processing specific item categories.
- Functional magnetic resonance imaging (fMRI) and electroencephalography (EEG) are utilized.
Purpose of the Study:
- To present a novel task and analytical pipeline for investigating category representations using EEG data.
- To assess the utility of EEG data for neural decoding of object categories.
- To compare classification accuracy between image and word stimuli.
Main Methods:
- Developed a task where 30 participants viewed images and words of objects across five categories (Animals, Tools, Food, Scenes, Vehicles).
- Employed a consecutive presentation paradigm with a response task.
- Trained support vector machines on EEG data for category classification.
Main Results:
- Achieved significant category classification accuracy for both image and word trials, with images yielding higher accuracy.
- All category pairs were distinguishable for image trials, compared to only one pair for word trials.
- Parietal and Left Temporal electrodes were more crucial for image classification; patterns generalized across participants.
Conclusions:
- The developed EEG-based methods demonstrate high classification accuracies, particularly for image trials.
- These findings support the utility of EEG data for neural decoding of category representations.
- The methods can be applied to study neural representations during wakefulness and offline states.
