以模糊限制為基礎之教學代理人協商於遠距教學系統之應用－以程式設計課程為例

隨著網際網路的快速發展，以網際網路為基礎的遠距教學系統也應運而生，使得學習課程的方式不再是直接面對面的方式，而能透過網際網路達到網路學習的目的。但網路學習的成效也一直是受質疑的，建構一個真正讓每個學習者能夠自主地學習並提昇其學習動力，進而達到學習成效的網路教學系統，是目前在網路教學系統中常被討論到的課題。每個人都有不同的特質與個性，倘若要使每個學習者在學習上達到預期的學習成效，那麼因材施教是不可或缺的。一般的網路學習對學習者的評估大多是承續傳統教學的模式，以考試及平常成績為主要的評量方式，僅止是消極的傳道授業，而不是積極的因材施教。本研究將整個網路學習的歷程視為軟體代理人協商的過程，並以模糊限制為基礎提出一以代理人協商為機制之網路學習架構，不僅保留教學系統應有的傳道授業，更加入因材施教的智慧型教學，來輔助並提昇學習者的學習動力及成效。本研究之網路學習架構主要是由教學方式、老師及學生心理因素、電腦運算三方面組合而成。在教學方式中融合了建構式教學主義、行為式教學主義及合作學習等三種學習理論，各取其所長來提昇學習者的學習動力及成效。在心理因素方面提出了以代理人協商為機制的互動學習模式，藉由代理人內嵌的老師及學生模式，建議老師對學生因材施教的方式或學生對特定老師應有的學習態度及成效。最後，在電腦運算中使用模糊限制的解題方法，找出在特定教學目標下，某些人格特質其學習態度的表現所能獲得的可能學習成效。　　實驗結果證明，配合本研究網路學習架構學習的成員比傳統式教學的學生在平均學習成效上提昇了22.06%；在學習的時程上也平均減少了15.37%天，印證了將網路學習歷程視為代理人協商過程的有效性及時效性。

關鍵字

網路教學；建構式教學主義；行為式教學主義；合作學習；分散式模糊限制；教學代理人；代理人協商

並列摘要

The fast development of internet is consequent on the internet-based distance pedagogic system. To conduct a class, face-to-face is not the only style, it can be done by the web, also. But, the effect of web learning is still a question. One of the most frequently discussed issue in the web pedagogic field is: How can we build a web pedagogic system then students can utilize this system to achieve their goal of study. Each people have his own character and personality. Thus, if we wish that every student can reach their expectations on studying, to teach students in accordance with their aptitude is indispensable. In the traditional pedagogy, examination result is the major information for estimating a students studying achievement. This way is an act of omission, not enthusiasm. We initiate a creative concept considering the course of e-learning as the process of agent negotiation. The institute proposes this new e-learning architecture, which is a mechanism of fuzzy constraint-based agent negotiation. It is not only keeping the traditional education functionality, but also adding a kind of smart pedagogy in order to increase the learning effect of the students. In this research, we propose an intelligent e-learning framework, which is composed of pedagogic methods, teacher’s or student’s mental states, and algorithms of computing. In pedagogic methods, the constructivism, the behaviorism, and the collaborative learning theories are fused as a main learning basis to promote learning motive and achievement. In terms of mental states, a fuzzy constraint-based agent negotiation mechanism is proposed as an interactive learning model to suggest a pedagogic or learning strategy. Besides, the problem solving of fuzzy constraints is applied to conclude the possible learning achievement under a specific learning attitude in the computing algorithms. The experiment result has illustrated that our approach can promote the learning achievement up to 22.06% and may reduce the learning cycle down to 15.37% than the traditional pedagogy. It is demonstrated that our research is effective and useful.

並列關鍵字

e-Learning ； Constructivism ； Behaviorism ； Collaborative Learning ； Distributed Fuzzy Constraints ； Tutor’s agent ； Multi-agent systems

參考文獻

[Alavi 1994] Alavi, M., 1994. “Computer-Mediated Collaborative Learning: An Empirical Evaluation,” MIS Quarterly, Vol. 8, No. 2, pp. 159-174.

[Atkins 1993] Atkins, M. J., 1993. “Theories of learning and Multimedia application: An overview,” Research Paper in Education, pp. 251-271.

[Atolagbe 2002] Atolagbe, T. A., 2002. “E-Learning: The Use of Components Technologies and Artificial Intelligence for Management and Delivery of Instruction,” 24th Int. Conf. Information Technology Interfaces ITI 2002, Cavtat, Croatia, pp. 121-128.

[Clark 1985] Clark, R. E., 1985. “Confounding in educational computing research,” Journal of Educational Computing, Vol. 1, pp. 137-148.

[Clifford 1999] Clifford, A. L, 1999. “Networked Information Resource Discovery: an Overview of current Issues,” IEEE Journal on Selected Areas in Communications, Vol. 13, No. 8, pp. 1505-1522.

國際替代計量

以模糊限制為基礎之教學代理人協商於遠距教學系統之應用－以程式設計課程為例

主題瀏覽