Effects of artificial intelligence-based personalized learning on STEM reading comprehension

Samsu Somadayo, Mohamad Jamil, Rohati Hi Halil

Abstract


Science, technology, engineering, and mathematics (STEM)-based reading comprehension is an important skill in modern education, yet many students still experience difficulties in understanding scientific concepts, technical terminology, and complex STEM texts. Although artificial intelligence (AI)-based personalized learning has been increasingly implemented in education, limited studies have explained how this approach improves STEM reading comprehension (SRC) through cognitive and self-regulation processes. Therefore, this study aims to examine the effects of AI-based personalized learning (AIPL) on SRC by investigating the mediating roles of cognitive engagement (CE) and self-regulated learning (SRL). A quantitative approach using partial least squares structural equation modeling (PLS-SEM) was employed. Data were collected through questionnaires from 250 students from several schools in Ternate City, Indonesia. The findings revealed that AIPL significantly influenced CE, SRL, and SRC. SRL was identified as the strongest factor affecting SRC. Furthermore, CE and SRL significantly mediated the relationship between AIPL and SRC. The study concludes that AIPL can effectively improve SRC by promoting CE and independent learning processes.

Keywords


Adaptive learning; Artificial intelligence in education; Cognitive engagement; Self-regulated learning; STEM literacy

Full Text:

PDF


DOI: http://doi.org/10.11591/ijere.v15i6.39580

Refbacks

  • There are currently no refbacks.


Copyright (c) 2026 Samsu Somadayo, Mohamad Jamil, Rohati Hi Halil

International Journal of Evaluation and Research in Education (IJERE)
p-ISSN: 2252-8822, e-ISSN: 2620-5440
The journal is published by Institute of Advanced Engineering and Science (IAES).

View IJERE Stats

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.