Adaptive learning with human factors and Artificial Intelligence: associations with training effectiveness in programming education

This study develops and validates a human-centered adaptive learning system that integrates Human Factors Engineering (HFE) and Artificial Intelligence (AI) to support programming education. The system adjusts learning strategies based on learners' behavioral indicators and self-reported psychological states, including motivation, interest, and confidence. Grounded in adaptive learning theory, the study proposes and tests hypotheses regarding the associations and interaction effects of these factors on learning effectiveness. A single-group pre/post empirical design with 100 participants was employed, incorporating exploratory factor analysis, regression modeling, and user satisfaction surveys. Results indicate that both motivation and interest are significantly associated with improved learning outcomes, and their interaction demonstrates a synergistic effect. The system's modular architecture—comprising behavioral data collection, learner modeling, strategy generation, and feedback—was positively evaluated for usability and engagement. While the findings confirm theoretical associations within the adaptive environment, causal claims and comparative effectiveness against non-adaptive systems require future controlled studies. By combining ergonomic interface design with AI-driven adaptivity, this research contributes to educational ergonomics and adaptive learning literature, offering a replicable framework and practical insights for designing intelligent, user-aligned instructional systems. • A human-centered adaptive learning system that integrates Human Factors Engineering (HFE) and Artificial Intelligence (AI) to enhance programming education effectiveness. • The system dynamically adjusts learning content and strategies based on learners' behavior and psychological profiles. • The system's modular design—comprising data collection, learner modeling, personalized strategy generation, and real-time feedback—demonstrates high user satisfaction and pedagogical value. • This research not only contributes to adaptive learning and human factors literature but also offers practical insights for designing intelligent, user-aligned educational systems.