以正規概念分析方法建構超媒體學習工具

Developing a Learning Toolbar to Construct Hypermedia Materials based on Formal Concept Analysis

徐長愷(Chang-Kai Hsu)

指導教授 ： 賀嘉生

中原大學/工學院/電子工程研究所/博士(2006年)

https://doi.org/10.6840/cycu200600038

摘要

在資訊時代有效率的資訊檢索環境越來越重要。大多數的超媒體系統在網際網路中表現成辦結構化或是無結構的設計，這樣的狀況使得使用者在閱讀資料時顯得更困難去尋找相關連的資訊。而一般的網頁教材設計者在編輯一份教材或是文章時，可能著重在文字的排版、頁面的美化反而往往疏忽於教材架構以及知識組織的設計。 若能在文章中標注出一些關鍵字，可以讓讀者更能瞭解該篇文章的重點。

透過文章內預先選出的關鍵字，我們可以在多篇文章中分析這些關鍵字的出現會形成一種關聯關係。而此性質可以採用物件與屬性的分析發現，關鍵字之間會具有一種偏續關係，這種數學上得理論應用讓我們發現若能將此關係的階層性找出來，或許可以用來挖掘文章與文章之間的關聯性，因而應用此關聯性質可以產生連文章的推薦。

關聯性質的挖掘最早應用在資料探索的領域，透過最大資料項的挖掘演算法我們可以找出一種關聯規則。而此種基本精神如何應用於教材的知識架構上的關聯關係，本篇論文參考正規概念分析的作法將多篇文章內的關鍵字建立出一種關鍵字關聯絡。這是一種具有最小上限以及最大下限的一種階層圖形結構，在此種結構中的連接邊即可尋訪出關聯則。在透過關聯規則挖掘演算法的設計，本篇文章可以找出關鍵字與關鍵字之間的關聯規則。然而，將此關聯規則使用在當讀者閱讀文章時自動產生相關文章的推薦或是參考資料的提供，可以達到一種線上閱讀的知識引導功能。

最後，依據此理論，本篇論文實做一套線上閱讀的輔助工具列：K-Navi Toolbar。此工具列安裝於瀏覽器內，學習者不需要在登入任何系統或是開啟其他軟體，只要透過瀏覽器閱讀線上教材或是文章，即可使用K-Navi進行相關文章的推薦。學習者便可以非常容易的找到其他關聯的文章或是補充教材來進行學習。

關鍵字

關聯規則 ； 正規概念分析 ； 線上學習 ； 關鍵字關聯絡 ； 知識引導 ； 補充教材 ； 結構化文章

並列摘要

Efficient automatic information retrieval has become increasingly important in information society. Most information on the WWW is presented in the form of semi-structured or unstructured hypermedia material, contained as a mixture of loosely natural language text and multimedia units. Sufficient keyword association, which would suitable for obtain the references and complementary documents.
When a learner is reading a hypermedia material on the web, sometimes he/she may not understand the meaning of a specific keyword clearly. Therefore, the learner will need more references for that keyword at that moment. However, unfortunately, in the most of time, the learner will not find out. It is because of the editors of instructional materials who had never thought that will be a question mark in the learners' mind. Therefore, if the appropriate dependent documents that are associated with the keyword that the learner is looking for could be retrieved automatically and the original document structure could be reconstructed to more suitable for learning and reading, that will be perfect.
In this paper, the formal concept analysis (FCA) and the data mining technique – association rule methodology (ARM) are applying to create a Keyword Association Lattice (KAL), to analyze and using to discovery non-redundant association rules. Three stages of algorithm design are described: 1.KAL construction, 2. mines association rules in a KAL, 3.reconstruct hypermedia materials.
Finally, the results of this research, an experiment system is implement, named K-Navi Toolbar, for the knowledge navigation to demonstrate the possibilities of such methodology in adaptive web for an e-learning environment.

並列關鍵字

keyword association lattice ； formal concept analysis ； hypermedia material ； association rule ； complementary document ； keyword ； knowledge navigation ； e-Learning ； adaptive web ； structured document

參考文獻

[HCH05] J. S. Heh, S. Y. Cheng and C. K. Hsu, "Nested State-Transition Graph Data Sequenceing Model with Hierarchical Taxonomy through Radix Coding," Journal of Information Science and Engineering, Vol. 21 No. 3, pp. 579-605., May 2005.

[AAP01] R. C. Agarwal, C. C. Aggarwal, and V. V. Prasad, “A tree projection algorithm for generation of frequent itemsets,” Journal of Parallel and Distributed Computing, Vol.61, No.3, pp.350-371, 2001.

[ACH90] T. Anantharaman, M. Campbell and F. Hsu, “Singular extensions: Adding selectivity to brute-force searching,” Artificial Intelligence Vol.43, No.1, pp.99–109, 1990.

[Ago96] M. Agosti, “An Overview of Hypertext,” Information Retrieval and Hypertext, Ed. by M. Agosti and A. Sematon, Kluwer Academic Pub, pp. 27-47, Boston, 1996.

[AIS93] R. Agrawal, T. Imielinski, and A. Swami, “Mining Association Rules Between Sets of Items in Large Databases”, Proc. 1993 ACM SIGMOD Int'l Conf. Management of Data, pp. 207-216, Washington, D.C., May 1993.