Dynamic Two-Stage Rough Set Synthetic Evaluation Mechanism for Elucidating Effective Learning Styles in E-Learning Environments

Abstract

Ough set theory is considered to be a highly suitable approach for elucidating knowledge and deciding possible learning styles in any E-learning environments as it possess the potential of extracting knowledge from uncertain and imprecise data. In this paper, a Dynamic Two-stage Rough Set Synthetic Evaluation Model (DWRSSEM) is proposed for effective decision making. DWRSSEM is identified as the effective method for elucidating knowledge for identifying the learning styles as it incorporates a two-stage approach that integrates the significance of primary and multi-level sub-factors. In this model, the impact of primary and multi-level sub-factors towards the identification of learner's learning style are quantified through conditional reliable attribute and marginal reliable attributes found to be more efficient in identifying the learning styles and also for discriminating various learning styles exhibited by e-learners. The results confirm that the degree of accuracy facilitated by DWRSSEM is 23% superior to the benchmark rough set theory approaches considered for investigation. The results also proves that DWRSSEM improves the effectiveness and efficiency in identifying e-learners style by utilizing a Two-Stage Rough Set Evaluation Factor (OSRSEF) that increases the performance by 27%, 22% and 25% in terms of discrimination rate, precision and recall value than the baseline elucidating approaches.