Enhance Reading Comprehension from EEG-Based Brain-Computer Interface
- Publisher:
- SPRINGER-VERLAG SINGAPORE PTE LTD
- Publication Type:
- Chapter
- Citation:
- AI 2023: Advances in Artificial Intelligence, 2024, 14471 LNAI, pp. 545-555
- Issue Date:
- 2024-01-01
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
978-981-99-8388-9_44.pdf | Published version | 5.02 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Electroencephalography (EEG)-based brain-computer interfaces (BCIs) have emerged as a valuable technology for decoding human cognitive processes, including reading attention and cognitive loads. While previous studies have explored eye fixations during word recognition, the intricacies of brain dynamics involved in sentence comprehension in the temporal or spectral domains still need to be discovered. Addressing this gap is crucial for enhancing learning processes; thus, in this study, we propose the first acquisition and recognition of event-related potentials and spectral perturbations using channel and independent component analysis, based on sentence-level simultaneous EEG and eye-tracking recorded from human natural reading tasks. Our results showed peaks of brain activation evoked at around 162 ms (approaching 200 ms) after the stimulus (starting to read each sentence) in the occipital area, indicating the onset timing of human retrieving lexical and semantic visual information processing. Approximately 200 ms occipital area presented increased alpha power and decreased beta and gamma power, relative to the baseline. Our results implied that most semantic-perception responses occurred around 200 ms in alpha, beta and gamma bands to facilitate human reading representation. The implications of our study underscore the significance of EEG-based BCI applications in reading tasks, serving as a potential catalyst for improving cognitive attention and comprehension in end-user reading and learning experiences. By retrieving the intricate cognitive mechanisms underlying sentence comprehension, we pave the way for developing brain-computer learning strategies to optimise reading instruction and support a diverse range of users.
Please use this identifier to cite or link to this item: