Learning performance assessment approach using learning portfolio for e-learning systems

Abstract

Learning performance assessment aims to evaluate what learners learnt during the learning process. It has become a critical issue in the Web-based learning field. Traditional summative evaluation can be applied to evaluate the learning performance both for conventional classroom learning and Web-based learning. However, it only considers final learning outcomes without considering the learning progress of learners. This paper proposes a learning performance assessment approach which combines four computational intelligence theories including grey relational analysis, K-means clustering method, fuzzy association rule mining and fuzzy inference to perform this task based on the learning portfolio of individual learners. Experimental results indicate that the evaluation result of the proposed method is positive relevance with those of summative assessment. Namely, this method can help teachers to precisely perform the formative assessment for individual learner utilizing only the learning portfolio in a Web-based learning environment.