LearnOpt: Recovering the Latent Cognitive Structure of Standardized Examinations via Knowledge Graphs and Constrained Optimization
Researchers have developed LearnOpt, a system that uses knowledge graphs and constrained optimization to uncover the underlying cognitive structures within standardized exams. By analyzing historical question papers, LearnOpt identifies stable patterns in skills tested, which can shift with curriculum changes. The system generates personalized study plans based on these identified structures, demonstrating a modest but real improvement over frequency-based topic recommendations. AI
IMPACT This research could lead to more effective personalized learning tools by better understanding the cognitive demands of exams.