Dynamic adaptive algorithms in personalized literacy interventions: A data-driven analysis of vocabulary development outcomes

Abstract

This study assesses the effect of dynamic adaptive algorithms on Vocabulary Acquisition in personalized literacy programs. This paper examines how adaptive systems are superior to static methods of teaching by using methods from different fields. There were 120 elementary school students in the study, half of whom use an adaptive literacy system and the other half follow a static curriculum. Participants were selected with different backgrounds and similar vocabulary skills at the start. The Structural Equation Modeling and Nonlinear Autoregressive Exogenous models were used to analyze the data. Based on the findings, adaptive systems significantly enhanced Vocabulary Acquisition, with the most tailored treatments producing the highest improvements. Variables such as text complexity and presentation time, which can be adjusted to help students learn new words, were also identified in the study. AI-assisted teaching methods and the creation of individualized learning spaces to maximize literacy outcomes have real-world consequences for educational policy.