Application of Artificial Intelligence in Adaptive Gamification to Enhance Mathematics Learning: A Systematic Literature Review

Abstract

Gamification has been increasingly recognized in education as it can foster motivation, enjoyment, and learner engagement, particularly in mathematics learning, which requires systematic understanding; however, conventional gamification may not sufficiently address individual differences among learners, leading to the development of adaptive gamification that adjusts game elements to fit learner characteristics, especially when integrated with artificial intelligence (AI). This study aims to investigate the use of adaptive gamification elements in mathematics learning, compare the application of AI in developing adaptive gamification systems, and analyze trends with recommendations for future design. A systematic literature review was conducted using international academic databases, namely Scopus, ScienceDirect, and SpringerLink, resulting in the selection of five articles that met the inclusion criteria for analysis. The findings reveal that adaptive gamification in mathematics learning most commonly incorporates points, progress, and goals, representing performance-related elements that enhance extrinsic motivation and track learners’ advancement, while personal dimensions such as goals, challenges, and novelty are widely used to foster intrinsic motivation and address individual differences; in contrast, social and environmental dimensions are less evident, reflecting a tendency toward individualized rather than collaborative or context-based learning. Regarding AI applications, most studies employed learner-facing and content-level AI to adjust instructional content and provide personalized interaction, while the use of AI to support teachers’ instructional decision-making and system-wide learning management is still insufficient. Overall, the results highlight a predominant focus on individual learner adaptation while underscoring the opportunity for broader and more comprehensive system-level integration in future designs.