DEVELOPMENT OF AN ALGORITHM FOR MASTERING THE TOPIC BY STUDENTS USING STATISTICAL METHODS

Abstract

This review article examines contemporary scientific approaches to the use of statistical methods for analyzing students’ topic comprehension processes and modeling their learning trajectories. The study aims to identify the role of statistical physics methods in explaining learners’ learning dynamics, detecting latent learning states, and constructing mastery algorithms. The review includes six recent studies published in the Scopus database over the past five years.

The analyzed works provide evidence for the effectiveness of Learning Analytics, Educational Data Mining, Hidden Markov Models, machine learning techniques, and statistical modeling in educational systems. According to the authors, students’ learning behavior represents a complex, multilayered system whose dynamics can only be fully revealed through statistical models. The review highlights recurring learning difficulties, gaps in the application of statistical methods, and the theoretical foundations for predicting learning progress.

This review offers a theoretical and methodological basis for studies aimed at constructing algorithms for student topic mastery. The findings demonstrate that the use of statistical methods enhances learning quality, enables the modeling of learning trajectories, and provides objective evaluation of students’ comprehension levels.