The MIND model a microlearning AI-integrated instructional design for enhanced learning outcomes

Abstract

Abstract In recent years, microlearning has gained significant attention due to technological advancements such as generative AI (GenAI), diverse learner needs, and a growing emphasis on improving learning outcomes. However, designing effective microlearning content remains challenging, as existing instructional design frameworks are inadequate for optimising learning outcomes. Therefore, this study developed a novel Microlearning AI-Integrated Instructional Design (MIND) Model to support effective instructional design to enhance learning outcomes. The model is grounded in multiple theoretical foundations, primarily the Technological Pedagogical Content Knowledge (TPACK) framework and the Factors Influencing Learning Outcomes (FIL) framework. To validate the MIND model, a mixed-methods approach was used with an intervention consisting of microlearning modules, comparing the MIND model (experimental group) with the ADDIE model (control group). Quantitative analysis using ANCOVA revealed that the MIND model significantly outperforms the ADDIE model in supporting effective instructional design to enhance learning outcomes, such as increased knowledge acquisition, understanding of module content, and improved knowledge application. Furthermore, t-test results indicated that learning outcomes within the MIND model group were consistent across gender, employment status, and locality, demonstrating inclusivity and accessibility. Kruskal–Wallis test showed a difference in learning outcomes across age groups, with younger learners achieving higher outcomes. Thematic analysis of qualitative data revealed that the modules developed using the MIND model featured media richness, interaction, engagement, self-concept, motivation, and satisfaction, contributing to learning outcomes. The MIND model serves as an innovative instructional design model that guides stakeholders in designing micro modules while remaining adaptable to conventional approaches, supporting flexible integration of cutting-edge technologies across formal, non-formal, and informal learning.