METHODOLOGY OF PERSONALIZED TEACHING OF COMPUTER SCIENCE BASED ON INTELLIGENT EDUCATIONAL SYSTEMS

Abstract

This article presents a methodology for personalized computer science education based on the integrated use of intelligent educational systems. The relevance of this research stems from the pressing need to overcome the severe limitations of traditional approaches, which often fail to take into account individual cognitive characteristics, the level of prior preparation, and the natural pace of learning. The primary goal of this work is to provide a scientific and methodological justification for an innovative adaptive learning model that enables dynamic and precise customization of individual learning paths. The proposed methodology is based on the deep integration of ontological modeling of the computer science subject area, modern machine learning algorithms for dynamic student profiling, and advanced methods of educational analytics. The intelligent system continuously analyzes the student's digital traces and actions, promptly identifies knowledge gaps, and automatically adjusts the content, optimal complexity, and logical sequence of educational modules, including practical tasks in algorithmization and programming. The scientific novelty lies in the original development of algorithms for semantic content selection based on knowledge graphs. The practical significance lies in the implementation of these principles into learning management platforms to enhance motivation, optimize course completion time, and improve final educational outcomes.