Artificial Intelligence-Based Adaptive Learning in Science Education to Enhance Higher-Order Thinking Skills, Personalization, and Learning Efficiency

Abstract

This study aims to analyze the effectiveness of Artificial Intelligence (AI)-based adaptive learning in enhancing students’ higher-order thinking skills (HOTS), personalization of learning, and learning efficiency in science education. The research employed a quantitative approach using a quasi-experimental design with a non-equivalent control group. The participants consisted of an experimental group that engaged in AI-based adaptive learning and a control group that received conventional instruction. Data were collected using a higher-order thinking skills test, a personalization questionnaire, and a learning efficiency test. The results showed that the experimental group achieved significantly higher post-test scores compared to the control group across all variables. The normalized gain (N-gain) analysis indicated that the experimental group reached a medium to high level of improvement, while the control group remained in the low to medium category. Statistical testing using an independent sample t-test revealed a significant difference between the two groups (p < 0.05). Furthermore, AI-based adaptive learning effectively improved students’ critical thinking, provided personalized learning experiences, and increased learning efficiency. These findings suggest that AI-based adaptive learning is an effective and innovative instructional approach for improving cognitive and instructional outcomes in science education.