Using AI-driven adaptive learning platforms in elementary education significantly improves both student academic performance and engagement levels across K-5 classrooms.
Objective: The main goal of this study was to investigate the impact of AI-driven personalized learning systems on academic performance and student engagement among K-5 students in elementary education settings. Specifically, the research aimed to evaluate how the Edmentum AI-driven adaptive learning system affected both academic outcomes and student engagement within kindergarten through fifth-grade educational environments, addressing a critical gap in empirical evidence regarding AI effectiveness in early elementary education.
Methods: This quantitative research study employed a pre-test/post-test design using diagnostic assessment data from the 2021-2022 and 2022-2023 academic periods. The study utilized secondary data analysis from students with diverse linguistic and cultural backgrounds at a suburban California school. Researchers applied SPSS descriptive statistics and linear regression analyses to examine the relationship between Edmentum usage duration and student outcomes. The methodology was grounded in behaviorist and adaptive learning theories, analyzing how AI systems provided real-time feedback and personalized learning pathways. Data collection included academic performance metrics, engagement measurements, and usage analytics from the Edmentum platform, with appropriate anonymization and ethical considerations for student privacy.
Key Findings: The study revealed several significant findings regarding AI's impact on elementary education. Linear regression analyses demonstrated that longer usage of the Edmentum system predicted better student academic results and enhanced student engagement levels. Post-test assessment results exceeded initial pre-test standards, indicating measurable academic improvement. The number of students reaching higher proficiency tiers showed a significant increase following AI system implementation. The research found that AI-based personalized learning tools effectively boosted student motivation and instructional responsiveness while helping to close achievement gaps among diverse student populations. Students who used the AI system more extensively showed greater academic gains and maintained higher levels of engagement throughout the learning process.
Implications: The findings contribute substantially to the field of AI in education by providing empirical evidence that AI-driven adaptive learning systems can effectively enhance both academic performance and student engagement in elementary settings. The study bridges theoretical frameworks from behaviorism and adaptive learning theory with practical classroom applications, demonstrating how AI tools can provide real-time feedback and personalized instruction that aligns with established learning principles. The research supports the integration of AI technologies in early education by showing their potential to address diverse learning needs, reduce achievement gaps, and promote equitable learning opportunities. These findings have important policy implications for educational administrators and teachers considering AI adoption, providing data-driven support for investment in adaptive learning technologies. The study also contributes to understanding how AI can transform teacher-student interactions by enabling more personalized, responsive instruction that adapts to individual learning pace and needs.
Limitations: The study acknowledges several important limitations that affect the generalizability of findings. The research was constrained by the use of secondary data, which limited the researchers' control over data collection parameters and variables. The study employed a single-site sample from one suburban California school, which restricts the applicability of findings to other geographic regions, demographic populations, or educational contexts. The focus on one specific AI platform (Edmentum) means results may not generalize to other AI-driven learning systems with different features or capabilities. Additionally, the study did not control for other variables that might influence student performance and engagement, such as teacher quality, home support, or concurrent educational interventions.
Future Directions: The research suggests several areas for future investigation to expand understanding of AI's role in education. Future studies should include multi-site research across diverse geographic and demographic settings to improve generalizability of findings. Researchers should conduct longitudinal studies to examine the long-term effects of AI integration on student learning outcomes and academic trajectory. Future research should explore how different AI platforms and features impact learning differently, comparing various adaptive learning systems to identify most effective approaches. Studies should investigate the optimal duration and intensity of AI system usage for maximum benefit. Additional research should examine how AI tools can be most effectively integrated with traditional teaching methods and explore the training requirements for teachers to maximize AI system effectiveness.
Title and Authors: "A Quantitative Study Investigating the Impact of Adaptive Artificial Intelligence in Students of Elementary Education" by Sehar Ellahi.
Published On: 2025
Published By: South College, Knoxville, TN (Doctoral Dissertation)