Title:

EEG-Based Language Proficiency Classification:​ A Power Spectrum and Cross-Spectrum Analysis​

Second language proficiency may be predicted with electrophysiological techniques. In a machine learning application, this electrophysiological data may be used for language instructors and language students to assess their language learning. This study identifies how electroencephalogram (EEG) power spectrum and cross spectrum data of the brain cortex relates to Spanish second language (L2) proficiency of 20 Spanish language students of varying proficiency levels at the University of New Hampshire. The two metrics for assessing cortex power and resources usage were event-related desynchronization (ERD)—a measure of relative change in power—of the alpha (8-12 Hz) brain frequency band , and alpha and beta (13-30Hz) brain frequency band coherence—a relative measure of spectral correlation between two cortical areas, respectively. Alpha ERD and alpha and beta coherence were calculated from EEG data collected while participants listened to three audio conditions of varying Spanish language difficulty. Significant differences in both alpha and beta coherence were found between proficiency groups. Higher proficiency Spanish L2 students exhibited more bilateral alpha and beta coherence dominance in the frontal and central cortices while the lower proficiency Spanish L2 students demonstrated greater unilateral alpha and beta coherence between the posterior cortices and Broca and Wernicke’s Area, the language processing centers of the brain.

Name

Comment*

Comments are viewable only by submitter

Captcha*