學習概念圖是一種圖形化工具，可幫助學習者組織、整合過去學習過的知識與新學習到的知識。本研究利用資料探勘之關聯規則技術，分析學生測驗作答資料，建構學習概念圖，在過去的研究中，多是基於學生得分資料為常態分佈下，將學生分成高分、中分、低分群分析，但學生的得分常不屬於常態分佈，本研究以學生-問題表(S-P Chart)為分群基礎，分析30131位國中三年級學生自然科試卷資料，將學生依學習狀況分為六群，並利用資料探勘之關聯規則技術，分別建構各群學生「力與運動」單元之學習概念圖，以了解學生對於概念理解的順序，並根據建構出的概念圖結果，針對學生學習上的迷失概念，提出建議補救學習路徑，進行補救學習，最後評估學習成效。
研究結果發現，依關聯規則所建構出的各群學習概念圖與課程編排順序有很大的差異，此外，以S-P Chart為分群基礎可建構出更細緻化的學習概念圖結果，A群與A’群在得分上皆屬高成就之學生，但有不同的學習概念圖結構，而B群與B’群學生也是如此，其在得分上之成就相同，但學習概念圖結構不同。S-P Chart從個別學生的作答反應，診斷學習狀況，而非只從得分或排名去衡量，因此可做出更準確的分群，達到更徹底的適性化教學。
在學習成效方面，參與補救學習的40位學生全體成績有顯著提升，以分群資料來看，B群、C群、C’群學生經補救學習後，學習成效有顯著進步。本研究結果可提供給教師教學與領域專家編排教科書時參考，另也可提供給系統開發者參考，以快速建構學習概念圖與補救學習路徑，開發即時且適性化的數位學習系統。

Concept maps are graphical tools that help learners organize and integrate new knowledge based on what they have learned. This study analyzes students’ assessment data applying association rule, one of the data mining techniques, to construct concept maps. In the previous studies, students were both divided into three groups which were high-score, middle-score, and low-score students group based on the percentage of students’ ranking only when the data of students’ scores follow normal distribution. However, the data of students’ scores usually don’t follow normal distribution. This study analyzes 30131 9th grade students’ assessment data and divides students into six groups based on student-problem chart (S-P Chart) to construct concept maps of mechanics subject for these six groups by applying association rule. This study suggests remedial learning paths for students based on the combination of their concept maps and misconceptions, and then analyses learning performances.
Results of this study show that the concept maps constructed by students’ assessment data are quite different from the one defined by school curriculum. A major finding is that the concept maps constructed based on student-problem chart can be more accurate and elaborated. The results indicate that the structure of concept map of group A is quite different from the one of group A’ even if group A and group A’ both belong to high-score students group, and the same as group B and group B’. It can be reasoned that dividing based on student-problem chart is more accurate and elaborated than dividing just by high-score, middle-score, and low-score students groups. Furthermore, it can achieve adaptive learning more thoroughly.
The result of learning performance indicates all participants have improvement significantly after they learned by suggested remedial learning paths, and the same as group B, group C, and group C’. The findings can be offered to the developers of digital learning systems so as to construct an adaptive remedial instruction system.

王富民 (2009)。以資料探勘技術分析學習評量資料─以國中力與運動概念為例(未出版之碩士論文)。國立臺灣師範大學圖書資訊學研究所碩士論文。臺北市。
余民寧(1997)。教育測驗與評量─成就測驗與教學評量。臺北市: 心理。
呂秋文(2000)。新數學科教材教法。臺北市：五南圖書。
佐藤隆博(1975)。S-P表の作成と解釋：授業分析：學習診斷のために。東京：明治圖書。
柯皓仁、楊雅雯、吳安琪、戴玉旻、楊維邦(2002)。個人化及群體化圖書館資訊服務初探。國家圖書館館刊，91(1)，161-195。
陳垂呈(2004)。利用關聯規則發掘圖書館個人化之書籍推薦。圖書資訊學刊，2(2)，87-103。
陳建宏(2000)。以色塊屬性關聯規則建立影像分類決策之研究(未出版之碩士論文)。國立臺灣師範大學資訊工程研究所學位論文。臺北市。
陳建傑(2010)。基於借閱目的之資料清理機制研究─以興趣目的為例(未出版之碩士論文)。國立臺灣師範大學圖書資訊學研究所碩士學位論文。臺北市。
彭文正(2001)。資料採礦：顧客關係管理暨電子行銷之應用。臺北: 數博網資訊。
曾憲雄、蔡秀滿、蘇東興、曾秋蓉、王慶堯(2005)。資料探勘 Data Mining。臺北: 旗標。
謝建成、林湧順(2006)。書目探勘讀者使用圖書館之行為。教育資料與圖書館學， 44(1)，35-60。
Ausubel, D. P. (1962). A subsumption theory of meaningful verbal learning and retention. The Journal of General Psychology, 66(2), 213-224.
Ausubel, D. P. (1963). The psychology of meaningful verbal learning: Grune & Stratton New York.
Cabena, P., Hadjinian, P., Stadler, R., Verhees, J., Zanasi, A., ., I. B. M. C., & ., I. T. S. O. (1998). Discovering data mining: from concept to implementation (Vol. 1): Prentice Hall Upper Saddle River, NJ.
Chiou, C. C. (2008). The effect of concept mapping on students’ learning achievements and interests. Innovations in Education and Teaching International, 45(4), 375-387.
Chung, H. M., & Gray, P. (1999). Special section: data mining. Journal of Management Information Systems, 16(1), 11-16.
Hall, C. (1995). The devil's in the details: techniques, tools, and application for database mining and knowledge discovery part II. Intelligent Software Strategies, 6(9), 1-16.
Hen, J., Kamber, M., & Pei, J. (2011). Data mining: concepts and techniques, 3/e. Morgan Kaufmann.
Hwang, G. J., Shi, Y. R., & Chu, H. C. (2011). A concept map approach to developing collaborative Mindtools for context‐aware ubiquitous learning. British Journal of Educational Technology, 42(5), 778-789.
Kelley, T. L. (1939). The selection of upper and lower groups for the validation of test items. Journal of Educational Psychology, 30(1), 17-24.
Kumar, V., & Chadha, A. (2012). Mining Association Rules in Student’s Assessment Data. International Journal of Computer Science Issues, 9(5), 211-216.
Lee, C. H., Lee, G. G., & Leu, Y. (2009). Application of automatically constructed concept map of learning to conceptual diagnosis of e-learning. Expert Systems with Applications, 36(2), 1675-1684.
Liao, S. H., & Chen, Y. J. (2004). Mining customer knowledge for electronic catalog marketing. Expert Systems with Applications, 27(4), 521-532.
McClure, J. R., Sonak, B., & Suen, H. K. (1999). Concept map assessment of classroom learning: Reliability, validity, and logistical practicality. Journal of research in science teaching, 36(4), 475-492.
Novak, J. D., & Cañas, A. J. (2008). The theory underlying concept maps and how to construct and use them. Florida Institute for Human and Machine Cognition Pensacola Fl, www. ihmc. us.[http://cmap. ihmc. us/Publications/ResearchPapers/T heoryCmaps/TheoryUnderlyingConceptMaps. htm], 284.
Novak, J. D., & Gowin, D. B. (1984). Learning how to learn: Cambridge University Press.
Roth, W. M., & Roychoudhury, A. (1993). The concept map as a tool for the collaborative construction of knowledge: A microanalysis of high school physics students. Journal of research in science teaching, 30(5), 503-534.
Sato, T. (1985). Introduction to student-problem curve theory analysis and evaluation. Tokyo: Mejji Tosho.
Tan, P. N. (2007). Introduction to data mining: Pearson Education India.