A machine learning-based usability evaluation method for eLearning systems

摘要: The research presented in this paper proposes a new machine learning-based evaluation method for assessing the usability of eLearning systems. Three learning methods (support vector machines, neural networks and decision trees) along with multiple linear regression are used to develop prediction models order discover underlying relationship between overall system its predictor factors. A subsequent sensitivity analysis is conducted determine rank-order importance predictors. Using both values scores, metric (called severity index) devised. By applying Pareto-like analysis, index ranked most important characteristics identified. case study results show that proposed methodology enhances determination problems by identifying pertinent could provide an invaluable guidance experts as what measures should be improved maximize targeted group end-users system. Usability assessment systems necessary challenging problem.Machine techniques effective tools assessments.Pareto-like can help devise values.Sensitivity rank