AI-Powered Adaptive Quizzing: Enhancing Personalized Learning, Student Engagement, and Performance in Digital Classrooms

Introduction: The integration of artificial intelligence (AI) into educational technology has transformed assessment practices by enabling more personalized and adaptive learning experiences. This study examined the development and effectiveness of an AI-powered adaptive quizzing system designed to adjust question difficulty in real time based on student performance and to deliver immediate feedback. Methods: The system employed learning analytics and machine learning algorithms to identify individual learning patterns and recommend targeted exercises aligned with students’ weaknesses. A mixed-methods design was implemented involving 200 high school students divided into an experimental group—using the AI-based adaptive quiz platform—and a control group relying on conventional assessments. Data were collected through pre- and post-tests, student surveys, and instructor interviews. Results: Findings showed that students using the AI-powered system demonstrated significantly higher engagement, improved knowledge retention, and greater motivation compared to those completing static quizzes. The adaptive mechanism facilitated more efficient learning by aligning question difficulty with students’ proficiency levels while providing timely corrective feedback. Conclusions: This study concluded that AI-driven adaptive assessments offer substantial advantages over traditional assessment formats and hold strong potential for enhancing personalized learning in digital classrooms. The findings contribute to the field of educational technology by providing empirical evidence of the role of AI in strengthening formative assessment and differentiated instruction.