Extending the diagnostic capabilities of artificial intelligence-based instructional systems

Abstract

Active problem solving has been shown to be one of the most effective ways to acquire complex skills. Whether one is learning a programming language by implementing a computer program, or learning calculus by solving problems, context-sensitive feedback and guidance are crucial to keeping problem-solving efforts fruitful and efficient. This article reviews AI-based algorithms that can diagnose student difficulties during active problem solving and serve as the basis for providing context-sensitive and individualized guidance. The article also describes the crucial role sensor-based estimates of cognitive resources such as working memory capacity and attention can play in enhancing the diagnostic capabilities of intelligent instructional systems.