Signal Exploring Fraction Comprehension and Interest in Elementary Education Through AI-Powered Personalized Learning

Summary

Kenneth Holman published a dissertation on arXiv (cs.CY) on August 5, 2026, examining AI-powered personalized learning during primary school fraction instruction, an area foundational to later mathematics and STEM achievement where empirical evidence remains limited, particularly for students with mathematics learning difficulties. The first manuscript presents a systematic review of research on AI in mathematics education published between 2020 and 2024. The second manuscript reports a quasi-experimental study evaluating Mathbot, a chatbot-based personalized learning platform, against business-as-usual classroom instruction, using repeated measures ANOVA to assess change in fraction comprehension and situational interest across time points. Results indicated modest improvements in fraction comprehension for students using Mathbot relative to traditional instruction, while changes in situational interest were not statistically significant. The findings suggest automated personalization did not displace the instructional role of the teacher, with teacher decision-making remaining central to student outcomes, and the work contributes classroom-based evidence to discussions about the capabilities and limits of adaptive AI systems, including accessibility and equity considerations for students with disabilities.