English digital reading achievement for East Asian students: identifying the key predictors using a machine learning approach

Abstract

ABSTRACT Students’ digital reading literacy has attracted increasing attention in the current digital era; however, few studies have been conducted to explore how factors at different levels influence students’ digital reading achievement. Grounded by socio-ecological theory, the current comprehensively explored the relative importance of 24 individual, microsystem, and mesosystem variables in predicting English digital reading achievement through the machine learning approach (i.e. random forest regression). The secondary data were retrieved from the Program for International Student Assessment (PISA) 2018, including 7,703 15-year-old students from Macao, Hong Kong, and Singapore. Our study identified 12 key factors that best predicted East Asian students’ English digital reading achievement. Among them, students’ socioeconomic status, subject-related ICT use during lessons, and interest in ICT ranked as the top three factors. The disparities in the roles played by disciplinary climate, gender, being bullied, immigrant status, and home language among the three economies were discussed.