臺灣博碩士論文加值系統

本研究的目的為依據國小學生於網路合作學習中同儕之間的對話，建立一適用於網路合作學習系統之同儕對話模型。
研究中透過兩位專家教師檢視網路合作學習的過程，將學生分為缺乏參與、重視協調、著重知識及善於社交四種類型，並由專家教師依據學生在網路合作學習活動中與同儕的對話內容，進行學生互動類型的判別及標示，再以專家教師的學生分類結果，利用類神經網路技術建立學生模型。研究結果顯示針對三個不同主題的網路合作學習活動所建立的學生模型之正確率分別為86%、85%和93%。此外，本研究為了在學習活動中提前預測學生類型，因此建立不同時段的學生模型，結果發現以5至20分鐘時段所建立的模型平均準確率（81%）最高。

The purpose of the study is to develop a generic model for peer dialogue in computer supported collaborative learning environments. The model was derived based on analyzing the dialogues of elementary school students participating in computer supported collaborative learning activities.
Two expert teachers identified four different patterns of student interaction: “Less-participated”, “Coordination-emphasized”, “Knowledge-focused” and “Social participating”. The expert teachers analyzed each of students’ dialogues to identify and label the characteristics of peer interaction. Accordingly, basing on the result of the analyses, neural network technique was adopted to develop peer interaction models. After verification on three concept-mapping activities, the accuracy rates of the peer interaction models developed were 86%, 85% and 93% respectively. To be able to predict student’s interaction during learning activities, the study further developed peer interaction models on the basis of different time periods. The result revealed the average accuracy rate was highest (81%) at the time period of the fifth through twentieth minutes after the learning activity begun.

一、 緒論 1
1.1 研究背景 1
1.2 研究目的 2
二、 文獻探討 3
2.1 學生模型的重要性 3
2.2 學生模型的意涵 3
2.3 建立學生模型的方法 4
2.3.1 相關系統 4
2.3.2 類神經網路 7
2.4 結語 11
三、 學生分類 12
3.1 資料來源 12
3.1.1 實驗活動 12
3.1.2 資料分析及轉換 12
3.2 專家教師 16
3.3 學生分類輔助系統 16
3.4 學生分類 19
3.5 學生分類結果 21
3.5.1 太陽系活動之學生分類結果 22
3.5.2 槓桿活動之學生分類結果 23
3.5.3 生物的生殖方式活動之學生分類結果 24
四、 建立學生模型 25
4.1 以類神經網路建立同儕對話模型 25
4.1.1 類神經網路架構設定 25
4.1.2 類神經網路環境設定 27
4.2 結果 28
4.2.1 完整對話資料之學生模型結果 28
4.2.2 活動部份對話資料之學生模型結果 33
五、 結論與建議 35
5.1 結論 35
5.2 建議 36
5.2.1 實際應用上的建議 36
5.2.2 後續研究之建議 36
中文部分 37
英文部分 38
附件一 太陽系參照圖 40
附件二 槓桿參照圖 41
附件三 生物的生殖方式參照圖 42
附件四 學生模型中權重值與偏權值 43

中文部分
邱瓊慧（2003）。網路合作學習環境中群組互動過程自動化監測、分析與引導之研究。行政院國家科學委員會輔助計畫案(NSC-92-2520-S-024-006)。
黃政傑、林佩璇（1996）。合作學習。台北：五南圖書公司。
葉怡成（2003）。類神經網路模式應用與實作。台北：儒林圖書公司。
蘇木春、張孝德（2003）。機器學習：類神經網路、模糊系統以及基因演算法則。台北：全華科技圖書公司。

英文部分
Andaloro, G., & Bellomonte, L. (1998). Student knowledge and learning skill modeling in the learning environment ''FORCES''. Computer & Education, 30(3), 209-217.
Brown, A. L., & Campione, J. C. (1994). Guided discovery in a community of learners. In K. McGilly (Ed.), Classroom lessons: Integrating cognitive theory and classroom practice (pp. 229-270). Cambridge, MA: MIT Press.
Carbonell, J. R. (1970). Mixed-initiative man-computer instructional dialogues (Technical Report BBN Report No. 1971). Cambridge, MA: Bolt Beranek and Newman, Inc.
Chiu, C. H. (2003). Exploring how primary school students function in computer supported collaborative learning. International Journal of Continuing Engineering Education and Lifelong Learning. Special Issue: Technological Support for New Educational Perspectives, 13(3/4), 258-267.
Constantino-González, M. A., & Suthers, D. D. (2002). Coaching collaboration in a computer-mediated learning environment. In Proceedings of Computer-Support for Collaborative Learning 2002 (CSCL 2002). Hillsdale: Lawrence Erlbaum Associates, Boulder, Colorado.
Constantino-Gonzalez, M. A., Suthers, D. D., & Santos, J. G. E. (2003). Coaching web-based collaborative learning based on problem solution differences and participation. International Journal of Artificial Intelligence in Education, 13(2-4), 263-299.
Dede, C. (1986). A review and synthesis of recent intelligent computer-assisted instruction. International Journal of Man-Machine Studies, 24, 329-353.
Harrer, A. (2001). Analysis of social interaction for construction of group models. In J. Moore, C. Redfield & L. Johnson (Eds.), Proceedings of World Conference on Artificial Intelligence in Education (AI-ED’01) San Antonio, TX. IOS Press.
Harwood, D. (1995). The pedagogy of the world studies 8-13 project: The influence of the presence/absence of the teacher upon primary children''s collaborative group work. British Educational Research Journal, 21(5), 587-611.
Jameson, A. (1995). Numerical uncertainty management in user and student modeling: An overview of systems and issues. User Modeling and User-Adapted Interaction, 5(3), 193-251.
Johnson, D. W., & Johnson, R. T. (1999). Learning together and alone: Cooperative, competitive, and individualistic learning (5th ed). Boston: Allyn and Bacon.
Katz, S., Lesgold, A., Eggan, G., & Gordin, M. (1993). Modeling the student in Sherlock II. Journal of Artificial Intelligence in Education, 3(4), 495-518.
Lingling, Z., Jun, L., & Jingui, P. (1999). An intelligent interface agent for web-based information retrieval. Paper presented at the Proceedings of the 1999 IEEE Workshop on Internet Applications, San Jose, California.
Martin, J. D., & VanLehn, K. (1993). OLAE: Progress toward a multi-activity, Bayesian student modeler. In P. Brna, S. Ohlsson, & H. Pain (Eds.), Artificial intelligence in education: Proceedings of AI-ED 93 (pp. 410-417). Charlottesville, Virginia: Association for the Advancement of Computing in Education.
Patel, A. (1998). A computer based intelligent assessment system for numeric disciplines. Information Services and Use, 18(1-2), 53-63.
Petrushin, V. A., & Sinitsa, K. M. (1993). Using probabilistic reasoning techniques for learner modeling. In P. Brna, S. Ohlsson, & H. Pain (Eds.), Artificial intelligence in education: Proceedings of AI -ED 93(pp. 418-425). Charlottesville, Virginia: Association for the Advancement of Computing in Education.
Petrushin, V. A., Sinitsa, K. M., & Zherdienko, V. (1995). Probabilistic approach to adaptive students’ knowledge assessment: Methodology and experiment. In J. Greer (Ed.), Artificial intelligence in education: Proceedings of AI -ED 95(pp. 51-58). Charlottesville, Virginia: Association for the Advancement of Computing in Education.
Posey, C. L., & Hawkes, L. W. (1996). Neural networks applied to knowledge acquisition in the student model. Information Sciences, 88, 275-298.