Signal Processing Research (SPR) Volume 4, 2015 www.seipub.org/spr
doi: 10.14355/spr.2015.04.012
69
Classification of Familiar or Strange English
Words using ERP
Yang Liu
1
, Jiacai Zhang
*2
College of Information Science and Technology, Beijing Normal University, Beijing, 100875, China
1
ly20liuyang@163.com;
*2
jiacai.zhang@bnu.edu.cn
Abstract
English vocabulary is the bricks of the language, and it’s important for English learners to handle accurately English words.
Words recitation or dictation is the most widely used simple test form in vocabulary quiz. However, some students do less well
in tests due to stress or even meltdown for exam. Here, we apply Brain fingerprinting (BF) in English vocabulary test. We
studied the Event Related Potential (ERP) components elicited by familiar English words and strange English words, and used
the ERP to decipher whether subject recognized the word presented in the screen. We analyzed the distinct ERP features related
to different stimuli (familiar and strange words), and further speculated whether subjects recognized the presenting words from
P300 by calculation correlations between different stimuli. The results of 8 subjects implied that familiar words recognized by
subjects could be detected from P300 with accepted precision and recall. This means that BF provides a novel alternative for
vocabulary quiz and opens the way for application in education, where concealed vocabulary related information stored in
mind was detected by measuring brain signals, such as electroencephalography (EEG).
Keywords
Brain Fingerprinting; P300; Event-related Potential; Vocabulary Quiz
Introduction
The strength of students’ vocabulary is very important to evaluate student English level. The more words students
are able to handle accurately, the better their chances of understanding English and making themselves
understood. Words recitation and dictation, as the simple vocabulary test, is most used in English exam.
However, explicit vocabulary exams always bring great pressure to students. Some students even feel excessively
worry about the upcoming exam and fear to be evaluated. Too much exam stress can cause individuals to perform
poorly on tests. Here, we employed Brain fingerprinting (BF) technique to evaluate students’ vocabulary implicitly.
BF is a technique that uses electroencephalography (EEG) to determine whether subject’s brain stored specific
information related to known or relevant item by measuring electrical brainwaves[1,2,3]. EEG Signal was recorded
when pictures or words was presented. A specific signal would be evoked in brain activity if the pictures or words
coincide with the memory of the subject. And this specific signal can be detected in electroencephalographic (EEG)
brainwaves, i.e. P300, a specific EEG event-related potential. So detection of P300 reflects whether known or
relevant information exists. In the previous literature, the P300-based detection has been well used in guilty
knowledge tests [3,8]. Then laboratory and filed tested at the FBI, CIA, and US Navy have got good results with 0%
errors [1,2]. In studies above, subjects usually had two roles, guilty or innocent, and researchers deciphered the role
from the brain responses. Where, three kinds of stimuli were employed: probe (P), irrelevant (I), and target (T). The
decision of subjects’ role is based on the fact that the brain's processing of known information, such as the details of
a crime stored in the brain, is revealed by a specific potential in P300 response.
In this study, we are aimed to decipher whether subjects recognize the stimuli words, rather than the subjects’ role.
We classified familiar words recognized by students from unacquainted words using EEG brain responses
recorded during subjects viewed the words on the screen. Experimental results demonstrated high classification
accuracy for all 8 subjects, showed that distinct P300 features were elicited by memory-relevant words, and this
paved the novel application of BF in education, such as vocabulary quiz.