Abstract
The purpose of this study is to explore and compare the variables that explain adolescents’ reading literacy and life satisfaction in Korea and Finland. To do this, the random forest method, machine learning technique, was applied to PISA 2018 data to explore the important variables among student or school related 262 variables, and multilevel modeling was utilized to test the significance of the selected important variables for Korean adolescents(n=6,650) and Finnish adolescents(n=5,649). Main results are as follows. The findings of the random forest revealed that 14 variables were commonly selected as important variables for both Korea and Finland; eight additional variables for Korea only and seven additional variables for Finland only were selected in reading literacy. Similarly, 13 variables were commonly selected for both Korea and Finland, five additional variables for Korea only and seven additional variables for Finland only were selected in life satisfaction. The results of the multilevel modeling revealed that ‘ICT available at home’ and ‘Student behaviour hindering learning’ were statistically negatively related to reading literacy for Korean adolescents. Moreover, ‘Family wealth’, ‘Attitude towards school: learning activities’, ‘Perception of cooperation at school’ and ‘Use of ICT at school in general’ were statistically positively related to Korean adolescents’ life satisfaction while ‘Afraid’ emotion was statistically negatively related to Korean adolescents’ life satisfaction. Based on the findings of the current study, implications for improving Korean adolescents’ literacy and life satisfaction as compared to Finnish adolescents are discussed.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have