Context-Aware Practice Problem Recommendation Using Learners’ Skill Level Navigation Patterns

The use of programming online judges (POJs) has risen dramatically in recent years, owing to the fact that auto-evaluation codes during practice motivates students learn programming. Since POJs have greater number problems their repository, learners experience information overload. Recommender systems are a common solution Current recommender used e-learning platforms inadequate for POJ since recommendations should consider learners’ current context, like learning goals and skill level (topic knowledge difficulty level). To overcome issue, we propose context-aware problem system based on navigation patterns. Our initially performs pattern mining discover frequent navigations find goals. Collaborative filtering (CF) content-based approaches employed recommend next levels sequence similarity measure is top k neighbors solved by learners. experiment results real-world dataset show our approach considering outperforms other systems.