隨著數位學習領域的標準趨向統一化，大部分的數位教材內容、學習元件(Learning Object)皆是以IEEE所制定的「學習物件後設資料」（learning objects metadata; LOM）來描述學習元件。我們可以輕易的在網路上搜尋到許多符合國際標準的學習元件，而這些學習元件可以一再的被不同的教學者重組、再利用。然而，隨著科技日新月異，在數位學習領域裡，新的學習概念也逐漸增多。
因此本論文提出一個以正規概念分析為基礎之本體論自動擴展機制，主要著重在分析LOM (Learning Object Metadata)欄位的特性，再配合一個經過改良的TF-IDF(Term Frequency-Inverse Document Frequency)資料前處理方法－Location weight TF-IDF(LTF-IDF)所擷取出重要的關鍵詞，接著藉由本研究提出的學習概念擷取機制，判斷是否有新學習概念之形成，並配合領域專家所建立的本體論(Ontology)，將新學習元件概念做新增的動作。

With the tendency towards the standard convergence in the field of e-learning, most of the e-learning contents and learning objects are described by learning object metadata (LOM) which is formulated by IEEE. People can easily search and fetch many learning objects which are conformed to the standard LOMs from internet repositories. Besides, these learning objects can be recombined and reused by different instructors. However, with the rapid development of technology, the new concepts of the learning objects have been changing and accumulating gradually. A course ontology already built for a specific domain needs a lot of effort by domain experts to renew when new concepts emerge.
Hence, this study proposes an Automatic Ontology Expansion Mechanism Based on Formal Concept Analysis and focuses on analyzing the character¬istics of learning object metadata (LOM) which is pre-processed by an adapted TF-IDF (LTF-IDF) methodology that can extract important terms. Then, by Automatic Learning Object Concept Extraction Mechanism proposed by this study, the formation can be judged if the concepts of the new learning objects are formed. Besides, the concepts of the new learning objects can be inserted according to ontology which is established by the experts of this domain

[1] Advanced Distributed Learning, S., "http://www.adlnet.gov/scorm/index.aspx."
[2] F. Chen and K. Han and G. Chen, ”An Approach to Sentence-Selection-Based Text Summarization” , Oct. 2002
[3] F. Sebastiani, “Machine Learning in Automated Text Categorization”, ACM Computing Surveys, Vol.34, No.1, March 2002, pp.1-47.
[4] FCA Concept Explorer http://sourceforge.net/projects/conexp.
[5] G. Salton, M. McGill, ”Introduction to Modern Information Retrieval,” McGraw-Hill New York, 1983.
[6] "IEEE LOM," http://projects.ischool.washington.edu/sasutton/IEEE1484.html.
[7] Jena – A Semantic Web Framework for Java , http://jena.sourceforge.net/
[8] Khan, L., "Ontology-based Information Selection," Ph.D. Dissertation, Department of Computer Science, University of Southern California, 2000.
[9] "LTSC Home Page — IEEE Learning Technology Standards committee," http://projects.ischool.washington.edu/sasutton/IEEE1484.html.
[10] M. C. Lee, D. Y. Ye, and T. I. Wang, ”Java Learning Object Ontology”, The 5th IEEE International Conference on Advanced Learning Technologies, pp.538-542, July 2005, Kaohsiung, Taiwan.
[11] N.F.Noy and D.L.Mcguinness, ”Ontology Development 101: A Guide to Creating Your First Ontology,” Stanford Knowledge System Laboratory Technical Report KSL-01-05 and Stanford Medical Informatics Technical Report SMI-2001-0880,Mar.2001.
[12] R. Neches, R. Fikes, T. Finin, T. Gruber, R. Patil, T. Senator, and W. R. Swartout, "ENABLING TECHNOLOGY FOR KNOWLEDGE SHARING," Ai Magazine, vol. 12, pp. 36-56, Fal 1991.
[13] T. R. Gruber, "A TRANSLATION APPROACH TO PORTABLE ONTOLOGY SPECIFICATIONS," Knowledge Acquisition, vol. 5, pp. 199-220, Jun 1993.
[14] The ACM Computing Classification System [1998 Version], http://www1.acm.org/class/1998/.
[15] The Porter Stemming Algorithm, http://www.tartarus.org/martin/PorterStemmer/.
[16] The Protege Ontology Editor and Knowledge Acquisition System, http://protege.stanford.edu/
[17] Welcome to Xerces, http://xerces.apache.org/.
[18] 蘇聖傑,“學習路徑自動化建構機制之研究”,成功大學工程科學研究所, 2007.
[19] 許正欣, “語意網上自動化建構本體論之研究”,輔仁大學資訊管理研究所, 2004.
[20] 陳偉洲, "基於本體論之學習元件自動分類演算法",成功大學工程科學研究所, 2006.
[21] 詹權恩 , "以詞彙關聯性詞庫為基礎之文件關鍵字擷取模式" ,
清華大學工業工程與工程管理研究所, 2004.
[22] 曾元顯, "關鍵詞自動擷取技術之探討"，中國圖書館學會會訊 106 期,1997.
[23] 林建宏, ”正規化概念分析建構電腦病毒特徵之知識本體”，雲林科技大學資訊管理研究所,2006.