A Systematic Review on Digital Literacy using Machine Learning Approaches

Authors

  • Kishore Babu Kalapala Research scholar, Sarvajanik University, Assistant Professor, Metas Adventist College, Surat, India. Author
  • Dr. Priti Shaileshbhai Patel Assistant Professor, Shree Ramkrishna Institute of Computer Education and Applied Sciences, Surat, India. Author

DOI:

https://doi.org/10.47392/IRJAEM.2024.0488

Keywords:

Digital Literacy, Digital Education, Digital Skills, Digital Technologies, Digital Competencies, Media Literacy, Information and Communication Technology (ICT) literacy, 21st Century Digital Skills, Machine Learning, Predictions, Student Knowledge Assessment, Learning outcomes

Abstract

As digital literacy becomes a foundational skill in the digital era, and digital skills become essential in today’s world, measuring and understanding digital literacy is more important than ever. This review explores how Machine Learning (ML) is being used to assess digital literacy, moving beyond traditional methods to create more personalized and insightful evaluations. We examined a range of studies that use ML techniques—like decision trees, neural networks, and support vector machines—to analyse digital skills in different educational settings. By identifying where individuals excel and where they may need support, these ML-driven approaches provide a customized view of digital literacy. Our findings show that ML models can not only improve the accuracy of digital literacy assessments but also open up possibilities for adaptive learning experiences, such as intelligent tutoring systems and personalized recommendations. While these approaches offer significant benefits, we also found challenges, particularly around integrating ML into diverse academic fields. This growing intersection between ML and digital literacy research provides new pathways for educators, policymakers, and researchers to promote and support digital skills. Looking ahead, there is a strong need to continue refining ML tools to make digital literacy assessment more inclusive, accurate, and adaptable across different learning contexts.

Downloads

Download data is not yet available.

Downloads

Published

2024-11-16