Examining ICT attitudes, use and support in blended learning settings for students’ reading performance: Approaches of artificial intelligence and multilevel model

Abstract

The increasing importance of learning context digitalization has necessitated investigations into the effects of information and communication technology (ICT)-related factors in blended learning settings on students' reading performance. Using data from 32 Organization for Economic Co-operation and Development countries from the latest cycle of the Programme for International Student Assessment (PISA) 2018 reading dataset, this study combines an artificial intelligence (AI) algorithm and hierarchical linear modeling (HLM) to examine the effects of student-level and school-level ICT-related factors in the blended learning setting on students' reading performance. Results show that students' perceived autonomy and competence in ICT, preference for different reading formats, quality of school ICT resources and school ICT use policies are positively related to reading performance, whereas school ICT use support for teachers and the teaching of ICT skills are negatively related to students' reading scores. The quadratic effects of students' interests in ICT, family and school ICT resources, and ICT uses are identified, showing an inverted U-shaped trend. The possible linear and quadratic moderation effects of school-level ICT-related features are also investigated. This study invites consideration of a combination of analytical methods for a comprehensive exploration of reading education and sheds light on how the delicate association of multilevel ICT factors in blended learning settings can contribute to the improvement of reading education. Instructors in blended learning settings should effectively integrate technology and appropriately apply pedagogies, and the design of blended learning should be sustainable and learner-friendly to exploit students’ learning potential.