Abstract
Learning performance assessment using learning portfolios or Web log data is essential in the Web-based learning field, owing to the rapid growth of e-learning systems globally and lack of assisted authoring tools for Web-based learning performance assessment. The traditional summative evaluation by performing examinations or feedback forms can be employed to evaluate the learning performance for both traditional classroom learning and Web-based learning environments. However, summative evaluation only considers final learning outcomes without considering learning processes of learners. This means that the interactively controlled learning based on the immediate feedback of learning performance cannot be performed in a Web-based learning system. Based on the reasons mentioned earlier, this study presents a data-mining-based learning performance assessment scheme by combining four computational intelligence theories, i.e., gray relational analysis (GRA), K-means clustering scheme, fuzzy association rule mining, and fuzzy inference, in order to identify the learning performance assessment rules using the gathered Web-based learning portfolios of an individual learner. Experimental results indicated that the evaluation results of the proposed scheme are very close to those of summative assessment results. In other words, this scheme can help teachers assess the learning performance of the individual learner precisely utilizing only the learning portfolios in a Web-based learning environment. Therefore, teachers can devote themselves to teaching and designing courseware since they save a lot of time in evaluating learning performance. More significantly, teachers could understand the factors influencing learning performance in a Web-based learning environment according to the obtained interpretable learning performance assessment rules. Besides, teachers can also tune teaching strategies for learners with various learning performances. This result also provides useful information to Web-based learning systems to perform personalized learning mechanisms for individual learners.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have