Development of an Adaptive Biology E-Module Using Generative AI and Personalized Learning to Enhance Self-Directed Learning

Abstract

This study aims to develop and evaluate an Adaptive Biology E-Module assisted by Visual Generative AI with a Personalized Learning Path to enhance students’ self-directed learning. The study employed a Research and Development (R&D) approach using the ADDIE model, consisting of analysis, design, development, implementation, and evaluation stages. The research was conducted with Grade X students at SMAN 6 Tanjungpinang, Indonesia. Data were collected through needs-analysis questionnaires, teacher interviews, diagnostic assessments, expert validation sheets, practicality questionnaires, self-directed learning scales, and pretest–posttest assessments. The developed e-module integrates diagnostic assessment, adaptive learning content, AI-generated biological visualizations, interactive activities, formative assessment, feedback, and personalized learning pathways based on students’ initial competence and learning progress. The projected results indicate an increase in the overall self-directed learning score from 65.3 before implementation to 91.0 after implementation, with improvements across learning awareness, learning strategies, learning activities, self-evaluation, and learning responsibility. These findings suggest that integrating adaptive learning mechanisms, scientifically validated Visual Generative AI, and Personalized Learning Paths has the potential to provide more individualized and meaningful Biology learning experiences. The study contributes a technology-enhanced instructional framework for promoting students’ autonomy and self-directed learning in Biology education