Pattern Analysis of Global AI Adoption and Digital Literacy Development in Science Education: Basis for a Recommender System Framework

The rapid growth of artificial intelligence (AI) technologies has transformed educational environments and created new opportunities for enhancing digital literacy in science education. However, variations in technological readiness, infrastructure, educational development, and AI adoption continue to influence the effectiveness of digital transformation initiatives across regions. This study analyzed global AI adoption patterns and digital literacy development using the Global AI in Education Dataset (2015–2026) comprising 1,360 observations from multiple countries and regions. A data-driven Intelligent Recommender System Framework integrating Educational Data Mining, Machine Learning, and Explainable Artificial Intelligence techniques was developed to identify digital literacy profiles and generate evidence-based recommendations. Digital Literacy Scores were computed using AI adoption, educational readiness, and technology access indicators and were subsequently classified into low, moderate, and high digital literacy profiles. Random Forest, Naïve Bayes, and Hybrid Voting models were utilized for pattern discovery and profile classification. Results revealed a continuous increase in digital literacy development from 2015 to 2026, accompanied by substantial growth in student AI usage, teacher AI usage, and school AI adoption. Random Forest achieved the highest classification performance with an accuracy of 94.49%. Feature importance analysis identified student AI usage, urban AI usage, internet penetration, education index, school AI adoption, and teacher AI usage as the most influential determinants of digital literacy development. Cluster analysis further revealed distinct educational environments characterized by varying levels of infrastructure readiness and AI engagement. Based on these findings, the proposed Intelligent Recommender System Framework generated targeted recommendations related to infrastructure expansion, teacher professional development, curriculum enhancement, AI literacy integration, institutional AI adoption, and digital inclusion initiatives. The framework provides a scalable and explainable decision-support mechanism that can assist educators, administrators, curriculum developers, and policymakers in promoting digital literacy and advancing AI-enabled science education.

@article{Cascolan2026,
  title     = {Pattern Analysis of Global AI Adoption and Digital Literacy Development in Science Education: Basis for a Recommender System Framework},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {7},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Honelly Mae S. Cascolan},
  doi       = {10.14569/IJACSA.2026.0170713},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170713}
}