Classification of Digital Learning Systems Using Data Envelopment Analsis and Data Mining Methods

• Main Authors: Chiao-Ling Huang, 黃巧菱
• Other Authors: Han-Ying Kao
• Format: Others
• Language: zh-TW
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/26501343034943807827

碩士 === 國立東華大學 === 網路與多媒體科技研究所 === 98 === After a long time of evolution, e-learning systems have developed various designs and platforms. However, the efficiencies of their uses and designs are seldom discussed. Most investigations adopt statistical methods to evaluate the effectiveness evaluation of e-learning system. This study aims at efficiency of e-learning system designs from user's cognition, instead of measuring the impacts on user's skills or knowledge sets. There are two primary objectives in this study, the first is to design an evaluation model for various e-learning systems with data envelopment analysis (DEA). Using questionnaires to collect user's responses, this study treats the data by fuzzy numbers and piecewise membership functions to increase the discrimination power of efficiency evaluation. The second one measures the design efficiency of a single e-learning platform from different groups of users. This study utilizes factor analysis to refine input and output factors and uses Bayesian network to build the classifier for predicting the efficiency. This study intends to provide further decision aids by integrating DEA and Bayesian network in e-learning system design efficiencies.