An enhanced genetic approach to optimizing auto-reply accuracy of an e-learning system

  • Authors:

  • Gwo-Jen Hwang;Peng-Yeng Yin;Tzu-Ting Wang;Judy C. R. Tseng;Gwo-Haur Hwang

  • Affiliations:

  • Department of Information and Learning Technology, National University of Tainan 33, Sec. 2, Shulin Street, Tainan City 70005, Taiwan, ROC;Department of Information Management, National Chi Nan University, Pu-Li, Nan-Tou 545, Taiwan, ROC;Department of Information Management, National Chi Nan University, Pu-Li, Nan-Tou 545, Taiwan, ROC;Department of Computer Science and Information Engineering, Chung-Hua University, Hsinchu 300, Taiwan, ROC;Information Management Department, Ling Tung University, Taichung 40852, Taiwan, ROC

  • Venue:
  • Computers & Education
  • Year:
  • 2008

Quantified Score

Hi-index 0.02

Visualization

Abstract

With the rapid development in Information Technology (IT), the Internet has become one of the central media for conducting learning. However, most of the existing web-based learning systems only provide stand-alone subject materials for browsing and may face some drawbacks. For example, if students encounter problems during the learning process, their learning performances could be significantly devastated due to no instant aid. As an on-line learning system may interact with thousands of students, it is almost impossible for the teachers or the teaching assistants to answer all the students' questions manually, which is not only inefficient, but also human laborious. To cope with this problem, an e-learning system that is able to automatically answer the students' questions on the fly based on the training cases given by the teacher will be presented in this paper. Moreover, an enhanced genetic approach is proposed to optimize the weights of keywords for each candidate answer according to the feedbacks provided by the students, hence more accurate answers can be provided in the future. Experimental results have shown that the developed system can provide more accurate answerers than existing approaches by employing the self-adjusting method.