隨著網際網路的蓬勃發展，網路上的各項協定逐漸標準化及應用技術日趨成熟，其中網路教學更是打破了時間與空間上的限制，改變了傳統教學模式，使得學習者可以更自主性的透過網路進行學習。另外，透過網路學習平台更能在不影響學生進行學習的情況下，自動的將學生瀏覽教材、線上討論等各項教與學的活動記錄於系統的網頁日誌內，此即學習者的學習歷程記錄。這些學習歷程記錄不僅將學習者的學習歷程記錄下來，其中更隱含了影響學習者學習成效的關鍵資訊，因此，如能及早得知影響學生學習成效的主要因素並預測可能落入學習障礙的學習者，教師便能針對不同學習行為偏差的學生給予個別的學習輔助，並修正其教學上的策略以提升學習者的學習成效。
另外，網路教學實為一種科技中介學習(TML, Technology Mediated Learning)的方式。許多科技中介學習研究文獻顯示資訊科技的使用可以增進學習的品質(Alavi,1994)，以及資訊科技扮演著對於學習促使者的角色。因此本研究即希望透過學生學習歷程檔案建置一決策分析機制，以提供不同時間點下的決策法則，讓教師可以即時掌握學生所有的學習行為及學習狀況並且即時修訂教學策略，學生亦可透過這一決策分析機制即時瞭解自己目前所處的學習狀況，修正自己的學習行為。然而，由於資訊科技的快速成長，目前可進行學生學習歷程分析的技術相當的多，也相當的繁雜，且缺乏一個整合性的分析，教師不知道什麼樣的分析技術最適合於自己所教授的課程。因此，本研究以目前最普遍用於資料分析的技術—資料探勘之相關技術，並比較傳統的統計分析方式嘗試為不同課程選擇適合搭配的分析工具，建置決策分析機制，以即時的呈現決策規則給教師作為預測學生學習行為的依據。

With the dynamic development of internet, various protocols and applications had been gradually matured on the network. The network has objective merits such as getting beyond the limits of time and space and change the tradition teaching model. Otherwise, the learning portfolios documented by on-line learning websites help teachers keep track of students’ learning process. With the educational information, teachers would be more able to observe students’ learning in real time and provide students with different decision rules under various time frames for teachers to understand both students’ learning behaviors and process instantaneously.
Nevertheless, technology mediated learning (TML) refers to an environment in which the learner interacts with learning materials, peers, and/or instructors that are mediated through advanced information technology. Recently, there have been increasing interests in investigating if TML can yield positive learning outcome. However, the rapid growth of information technology concerning analyzing the learning track is of various analytic approaches and thus is really complicated. The lack of one integrative analysis of all the possible use of the diverse analyzing frameworks prevents teachers from picking one most appropriate analyzing framework for their own teaching. Accordingly, this research compares and contrasts the most prevailing data analyzing technique－data mining and the traditional statistical analysis approaches with the hope to allocate matching analyzing tools for various kinds of courses as well as to provide teachers with immediate decision rules as bases for predicting students’ possible learning behaviors.

第一章 緒論 1
1.1 研究背景與動機 1
1.2 研究目的 4
1.3 研究對象 5
1.4 論文架構與研究流程 6
第二章 文獻探討 8
2.1 科技中介學習 8
2.2 衡量學習成效指標 11
2.3 學習歷程記錄與相關研究 13
2.4 資料探勘相關理論 14
2.5 決策樹相關理論與應用 15
2.6 倒傳遞類神經網路相關理論與應用 22
2.7 統計相關理論與應用 30
第三章 研究方法 31
3.1 研究架構 31
3.2 分析變數 32
3.3 研究步驟 35
3.4 決策樹分類的產生、分析與整理 40
3.5 倒傳遞類神經網路分類的產生、分析與整理 42
3.6 統計分類的產生、分析與整理 45
3.7 分析技術的準確性及決策規則的驗證 46
第四章 資料分析結果與討論 48
4.1 決策樹法則分析結果 49
4.2 倒傳遞類神經分析結果 56
4.3 統計分析結果 61
4.4 綜合結果比較 64
4.5 建置決策分析機制 67
第五章 結論與建議 74
5.1 研究發現 74
5.2 研究貢獻 77
5.3 研究限制 79
5.4 研究建議及未來研究方向 79
參考文獻 81
中文參考文獻 81
英文參考文獻 82

中文參考文獻
[1]朱彩馨，以科技中介架構探討線上學習成效之詮釋研究，國立中山大學資訊管理研究所博士論文，2001。
[2]邱永祥，運用類神經網路與資料探勘技術於網路教學課程推薦之研究年，朝陽科技大學資訊管理研究所碩士論文，2003。
[3]邱美珍，”決策樹學習法中連續屬性之分類研究”，中原大學資訊工程研究所碩士論文，1996。
[4]洪明洲，網路教學，台北：華彩，1999。
[5]施柏屹，「倒傳遞類神經網路學習收斂之初步探討」，中央大學機械工程研究所碩士論文，2000。
[6]姚永錩，網路大學建置之關鍵成功因素探討–以『中山網路大學』為例，國立中山大學資訊管理研究所碩士論文，2003。
[7]陳年興、謝盛文、陳芸霈，從學習歷程記錄檔動態建構決策樹以支援適性化教學，中華民國資訊學會通訊，6(3)，pp.11-24，2003年。
[8]陳國棟，Discover SCORM portfolio online analysis and decision-make supporting，第三屆網路教學系統平台與內容標準化研討會，2003。
[9]童宜慧、張基成，”網路化學習歷程檔案系統之建構與評鑑-一個電子化的真實性學習評量工具”，遠距教育，第13/14期合刊，pp.78-90，2000。
[10]葉怡成，”類神經網路模式應用與實做.”第八版，儒林出版社，2003。
[11]廖聖傑，從學習歷程檔案建構決策樹以支援網路教學，國立中山大學資訊管理研究所碩士論文，2003。
[12]劉惠如，整合式網路教學之教學設計與評量，國立中山大學資訊管理研究所碩士論文，1999。
[13]劉晨鍾，網路學習歷程之知識探索：學習效能評鑑之工具，國立中央大學資訊工程研究所博士論文，2000。
[14]蘇木春、張孝德，機械學習：類神經網路、模糊系統以及基因演算法則，全華科技圖書股份有限公司，台北，2002。
[15]Technology Review雜誌（麻省理工學院2002年1月出刊）
英文參考文獻
[1]Alavi, M., and Leidner, D. E. “Research Commentary: Technology-mediated Learning - A Call for Greater Depth and Breadth of Research.” Information Systems Research, Vol.12, No.1, 2001, pp.1-10.
[2]Alavi, M., Yoo, Y. and Vogel, D. R. “Using information technology to add value to management education.” Academy of Management Journal, Vol.40, No.6, 1997, pp.1310-1333.
[3]Alavi, M., Wheeler, B. C. and Valacich, J. S. “Using IT to Reengineer Business Education: An Exploratory Investigation of Collaborative Tele-learning.” MIS Quarterly, Vol.19, No.3, 1995, pp.293-313.
[4]Alavi, M. “Computer-Mediated Collaborative Learning: An Empirical Evaluation.” MIS Quarterly 18, No.2, June 1994, pp.150-74.
[5]Chen-Chung Liu, Gwo-Dong Chen, Chin-Yeh Wang "Student modeling for performance assessment using Bayesian network on web portfolios" Journal of Educational Computing Research, Vol.27, No.4, 2002, pp.437-469.
[6]Chen, M. S., J. Han, and P. S. Yu: Data mining: An overview from a database perspective, IEEE Transactions on Knowledge and Data Engineering, Vol.8, No.6, 1996, pp.866-883.
[7]Fishwick, P.A. and Tang,Z.. ”Time series forecasting using neural Nets, Reading” Addison Wesley publishing Co, 1991.
[8]Freitag, D., McCallum, A., Mitchell, T., Nigam, K. and Slattery, S., Learning to extract symbolic knowledge from the world wide web, Proceedings of American Association for Artificial Intelligence,1998.
[9]Fuller, R., Data Mining Overview, http://www.datawarehouse.com/,2002.
[10]Han, J.: Data Mining, in J. Urban and P. Dasgupta (eds.), Encyclopedia of Distributed Computing, Kluwer Academic Publishers, 1999.
[11]Hiltz, S. R., and Wellman, B. “Asynchronous Learning Networks As A Virtual. Classroom,” Communications of the ACM, Vol.40, No.9, 1997, pp.44-49.
[12]Ives, B. “Transforming the learning industry” MIS Quarterly, Vol.18, No.1, Mar 1994, pp.V-Viii.
[13]Jiawei Han, Micheline Kamber, Data mining concepts and Techniques, 2003.
[14]Joachims, T., Text Categorization with Support Vector Machines: Learning with Many Relevant Feature, 10th European Conference on Machine Learning, 1998.
[15]Kaastra, I. and Boyed,M. “Designing a neural network for forecasting financial and economic time series.” Neurocomputing. 10(3), 1996, pp.215-236.
[16]Kiser, K. “E-Learning Takes Off At United Airlines,” Training, Dec 1999, pp.66-72.
[17]Leidner, D., and Fuller, M. “Improving Student Learning of Conceptual Information: GSS Supported Collaborative Learning vs. Individual Constructive Learning,” Decision Support Systems, Vol.20, No.2, 1997, pp.149-63.
[18]Leidner, D. E., and Jarvenpaa, S. L. “The information age confronts education: Casestudies on electronic classrooms,” Information Systems Research Vol.4, No.1, 1993, pp.24-55.
[19]Leuthold, J. H. “Is Computer-Based Learning Right for Everyone?” In Proceeding of 32nd Hawaii International Conference on System Sciences, 1999.
[20]Levy, M. Computer Assisted Language Learning, New York: Oxford University Press, 1997.
[21]Marki, R. H., Maki, W. S., Patterson, M. and Whittaker, P. D. “Evaluation of a Web-based Introductory Psychology Course: I. Learning and Satisfaction in On-line Versus Lecture Courses,” Behavior Research Methods, Instruments and Computers, Vol.32, No.2, 2000, pp.230-239.
[22]Pastore, M. “Companies, Universities Moving Toward E-Learning,” http://cyberatlas.internet.com/markets/education/article/0,,5951_737341,00.html, April 9, 2001.
[23]Piccoli, Gabriele. “Web-based virtual learning environments: A research framework and a preliminary assessment of effectiveness in basic IT skills training,” MIS 127 Quarterly, Vol.25, No.4, 2001, pp.401-27.
[24]Redmond, M., and Sweeney, N. “Multimedia Production: Non-linear Story-telling using digital technologies,” in Contextual Media. E. Barrett, and Redmond, M. (eds.), MIT Press, 1995, pp.87-102.
[25]Salchenberger, L.E. “Neural networks: A new tool for Predicting thrift failures.” Decisions Sciences, 1992, pp.899-916.
[26]Schutte, J.G. “Virtual Teaching in Higher Education: The New Intellectual Superhighway or Just Another Traffic Jam,” California State University, CA, 1997. Available: www.csun.edu/sociology/virexp.htm.
[27]Thatcher, M. “Campus Fugit,” People Management, Vol.3, Sep 1998, pp.54-55.
[28]Thuraisingham, B.: A primer for understanding and applying data mining, IT Professional, Vol.2, No.1, 2000, pp.28-31.
[29]Watters, C., Conley, M. and Alexander, C. “The Digital Agora: Using Technology for Learning in the Social Science,” Communications of the ACM, Vol.41, No.1, 1998, pp.50-57.
[30]Webster, J., and Hackley, P. “Teaching Effectiveness in Technology-MediatedDistance Learning,” Academy of Management Journal, Vol.40, No.6, 1997, pp.1282-310.
[31]Zaiane, O.R.,Xin, M. & Han, J., Discovering Web Access Patterns and Trends by Applying OLAP and Data Mining Technology on Web Logs, Advances in Digital Libaries Conf., Santa Barbara, CA, 1998, pp.19-29.