TITLE:
Efficacy of an Online Reading Intervention Program “Literacy Pro” in Classifying Students as “At Risk” and “Not at Risk” among ESL School Students—A Logistic Regression Analysis
AUTHORS:
Sheeba Jojo, Chanintorn Jittawiriyanukoon, Varughese Kizhakkacharuvil John
KEYWORDS:
Classification Accuracy, ESL, Literacy Pro, Logistic Regression, Reading Comprehension, Sensitivity, Specificity
JOURNAL NAME:
Creative Education,
Vol.13 No.3,
March
30,
2022
ABSTRACT: The purpose of this study is to test the
classification accuracy of an online reading comprehension program “Literacy
Pro” in classifying students as “at risk” and “not at risk”. Data was collected
from the school records of an international school operating in Dubai, UAE. The
students of this school are non-native English speakers or they learn English
as a Second Language (ESL). The sample was taken from two grades—grade 7 and
grade 10. A logistic regression analysis (simple and multiple) was done to test
the classification accuracy in terms of the sensitivity and specificity rule.
The results of the current study show a sensitivity level of 0.76 and 0.94 for grade
7 and 10 respectively, whereas the corresponding specificity levels are 0.99
and 0.97 respectively. The overall accuracy of the model for grade 7 and 10 is
89.9% and 94.4% respectively in simple logistic regression whereas the
corresponding values are 89.9% and 95.6% in multiple logistic regressions. Therefore, it can be
concluded that the reading intervention measure of “Literacy Pro” is highly
accurate in classifying students as “at risk” and “not at risk”. The area under
the curve (AUC) value was obtained as 0.8754 and 0.9512 for grade 7 and 10
respectively for the ROC curves of the model. Hence, the classification
accuracy of grade 10 is excellent and that of grade 7 is good as per the
generally accepted standards for the online reading comprehension program
“Literacy Pro”.