Pattern-based Knowledge Component Extraction from Student Code Using Representation Learning

This paper proposes an automated framework for extracting Knowledge Components from student code submissions in computer science education by identifying recurring structural patterns in Abstract Syntax Trees, validated through learning curve analysis and Deep Knowledge Tracing. The work focuses on modeling student knowledge acquisition in programming courses to enable personalized learning and adaptive feedback.

Effective personalized learning in computer science education depends on accurately modeling what students know and what they need to learn. While Knowledge Components (KCs) provide a foundation for such modeling, automated KC extraction from student code is inherently challenging due to insufficient explainability of discovered KCs and the open-endedness of programming problems with significant structural variability across student solutions and complex interactions among programming concepts.

Source

Framework Categories

Tool Types

Tags