Abstract
Recommendation systems depend on appropriate decision making in order to personalize information content upon an individual's user needs, preferences, interests and browsing behaviors. These systems usually neglect the user's ability and the difficulty level of the recommended item. Therefore, this study proposes a comprehensive recommendation system to provide adaptive learning, which is composed of two main agents: PIRT_Recommendation agent, helping the learner to personalize learning resource based on Polytomous Item Response Theory (PIRT), which considers both the difficulty of the learning resource and the ability of the learner, and VPRS_Recommendation agent, providing decision rules as an instrument or guide for learner's self-assessment based on improved Variable Precision Rough Set (VPRS). Experimental results show that the proposed system can exactly provide closer learning resource with appropriate feedback to the learner, resulting in increased the learning efficiency and learning performance.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have