Aggregating evaluation using dynamic weighted intuitionistic fuzzy approach for concept sequencing in an e-learning system

Abstract

Adaptation of learning concepts in an e-learning system for individuals depends on his ability to learn. Learners are perplexed in hyperspace when learning concepts are displayed in an unstructured form. To provide an effective learning path, sequencing of learning concepts and contents should be according to learner's orientation and individualised access support. Therefore to reduce disorientation, each learner should get path based on his level of knowledge acquisition and learning style. However, most of the e-learning systems determine the learner's knowledge through expert weight given to a learning concept whereas in this work weights of learning concepts are determined during learners' assessment itself. For this, we applied intuitionistic fuzzy theory approach and proposed a dynamic weighted concept intuitionistic fuzzy averaging (DWCIFA) operator to personalise the sequencing of learning concepts based on assessment results. We tested the algorithm on synthetic data set, created using quasi random generator function in Python. The results prove that it improves navigation, and also helps student to achieve deep knowledge in the domain.