Enhancing Personalized Learning in Programming Education through Generative Artificial Intelligence Frameworks: A Systematic Literature Review

Abstract

Generative Artificial Intelligence (Gen AI) has revolutionized education by enabling personalized learning in computer programming, improving engagement and outcomes. Despite its potential, challenges like accuracy, coherence, and relevance persist, necessitating targeted solutions to maximize its educational impact. A systematic literature review (SLR) was conducted following PRISMA guidelines, analyzing studies from 2019–2024 across databases like IEEE Xplore, ACM Digital Library, and Scopus. The multi-stage selection process identified 42 articles out of an initial 120, focusing on adaptability, relevance, coherence, and accuracy in AI-driven educational tools. Key factors enhancing Gen AI effectiveness were adaptability (33%), contextual relevance (24%), coherence (21%), and evaluation metrics (12%). Prompt engineering (10%) emerged as a critical strategy. Adaptive systems dynamically tailored content to learners, while relevance-enhancing tools aligned materials with educational goals. Evaluation metrics and coherence frameworks improved logical and functional accuracy. Findings highlight Gen AI’s transformative potential in programming education, demonstrating improved engagement and alignment between theoretical and practical learning. However, challenges in coherence, accuracy, and ethical concerns like fairness and bias remain areas for further exploration. Generative AI offers scalable opportunities for personalized programming education. Addressing accuracy, coherence, and ethical challenges will enhance its integration into learning environments. Future research should focus on long-term evaluations, advanced evaluation frameworks, and ethical guidelines to ensure inclusive AI use.