Identifying Factors Affecting PISA 2018 Digital Reading Literacy via Machine Learning Algorithms

• In Event: Applications of New Analysis Methods to Large-Scale Assessments

Abstract

Digital reading literacy is an essential skill for 21st-century citizens who are engaged in complex digital-based communication. However, researchers found that adolescents struggle with evaluating digital content. This study aims to identify factors affecting the digital reading literacy of n = 37,514 15-year-old students from 33 countries participating in the PISA 2018 using the Lasso and Random Forest machine learning algorithms. Findings showed that Lasso outperformed Random Forest in predicting students’ digital reading literacy. The Lasso method found that Meta-Cognition: Assess Credibility and Availability of ICT Devices were factors associated with digital reading literacy. Instructors and administrators could consider teaching students to use metacognitive strategies and providing more ICT opportunities to promote digital reading literacy.

Authors

• Hao-Yue Jin, University of Alberta

• Lydia Marion González-Esparza, University of Alberta

• Chang Lu, Shanghai Jiao Tong University

• Maria Cutumisu, McGill University