TDNet Discover

The dissertation evaluated how the Edmentum AI-driven adaptive learning system affected both academic performance and student engagement within K–5 educational settings. This research employed quantitative methods to examine diagnostic assessment data from the academic periods of 2021–2022 and 2022–2023 based on principles of behaviorist and adaptive learning theories. The study sample comprised students with diverse linguistic and cultural backgrounds from a suburban Californian school. SPSS descriptive statistics and linear regression analyses demonstrated that longer usage of Edmentum forecasted better student academic results along with enhanced student engagement. The results from post-test assessments exceeded initial pre-test standards while the number of students reaching higher proficiency tiers showed a significant increase. Recent studies showed that AI-based personalized learning tools work well to boost student motivation and instructional responsiveness while closing achievement gaps. Despite the constraints of secondary data and a single-site sample this study provided valuable insights for developing future adaptive education technologies. The study enriched discussions about personalized learning and equity as well as data-driven teaching by providing recommendations for teachers and school leaders on how to use AI technology to develop customized educational tracks for primary school students.