隨著資訊科技快速成長，數位學習的發展也漸趨成熟，數位學習不僅能提供隨時隨地、無遠弗屆學習的機會，也能有效幫助特教學生在學習上的成長。特教學生由於有注意力缺陷、短期記憶差、抽象推理能力薄弱、學習緩慢等特質，適性化的學習引導，能增加學生學習興趣，提升其相關知識能力。合作學習是一般常見的學習方式，不但可以幫助學生互相成長，更能增進學生與人相處的社會互動能力。
　　有鑑於此，本研究參考數位學習、合作學習及適性化學習等理論，設計「具適性化學習引導之數位合作學習模式」，並依此模式設計「適性化學習引導方法」與開發其實現技術，並以數學學習為應用，依此模式建構具「異質分組、動態學習路徑規劃以及適性化輔導」機制之「適性化數位合作學習平台」，並於該平台進行實驗，以檢驗此一「適性化學習引導模式」之可行性與妥適性以及對身心障礙學生數學能力提升成效。
本數位合作學習平台先根據學生個人特質進行異質分組與角色分派，再依據小組的知識結構規劃學習路徑，學習過程中針對小組之學習狀況給予適性化的提示與回饋，並針對小組成員個別之錯誤類型提供適性化輔導。實驗證明身心障礙學生使用本數位合作學習平台能顯著提升數學學習成效。

Abstract
An Adaptive Learning Guidance for Collaborative E-Learning: Mathematics Learning of Special Education Students as an Example
Zhi-Quan Wang
Yuh-Min Chen
Hui-Chuan Chu
Institute of Manufacturing Information and Systems
National Cheng Kung University

SUMMARY

This work develops an adaptive learning guidance for use in the benefit of students with special education needs a collaborative e-learning environment. When such students are learning, a model of the knowledge of a learning group is used to create a dynamically adaptive learning path. A genetic algorithm is used to group students. Then, an Apriori algorithm is used to generate the group knowledge model. The developed knowledge model that uses the developed algorithm to generate the adaptive learning path. Finally, a collaborative e-learning platform is generated to enable students to learn via the learning path. Experimental results indicate that groups that received adaptive learning guidance exhibited improved learning performance. The experimental results herein also revealed that students with moderate knowledge gained greater benefit than those with more knowledge.

Key words: Collaborative learning, E-learning, Adaptive learning, Heterogeneous grouping, Learning path

INTRODUCTION

In recent years, countries around the world have begun to focus on the education of disadvantaged students, actively promoting policies to help disadvantaged students to catch up with other students. More advanced countries have longer historical periods of the development of special education, and special education students in such countries receive more attention. Special education students differ in physical and mental developmental and learning-related characteristics, as well as other respects, from average students. Because learning for such students is harder than for general students, learning outcomes are relatively poor, and those students are more difficult to teach using traditional methods. Teachers must pay correspondingly more attention to them.
Research (Rovai, 2000) has demonstrated that e-learning differs from traditional classroom learning, and can help special education students to learn more effectively. However, most e-learning systems lack appropriate learning guide mechanisms, so learners are likely to experience cognitive overload and disorientation, reducing the effectiveness of learning. Slavin (1985) regarded cooperative learning as the goal of structured systematic teaching strategies. If teachers do not understand their students well, and they fail to teach in a manner that takes into account the heterogeneity of their students, then learning suffers.
E-Learning
"E-Learning", formerly known as distance learning, emphasizes the use of electronic media to transmit teaching content, two-way interactive teaching, and the creation of a digital learning environment.
Cooperative learning
Cooperative learning emphasizes heterogeneous groupings and group cooperation. Team members work together to accomplish a common goal. Some scholars (Dugan, Kamps, Leonard, Watkins, Rheinberger, & Stackhaus, 1995) have utilized cooperative learning to help autistic children in two fourth-grade classes, and they found an increase in the weekly quiz scores of individual children with autism during the period of intervention, improved participation and focus, relative to a reference period, and increased social interaction with peers.
Computer-supported Collaborative Learning
Research over the last decade has confirmed that the network can increases the number of opportunities that students can take to participate actively in cooperative learning. Scifres & Behara (1998) asserted that allowing remote network team members to interact continuously is important to a network of cooperative learning.
This work develops the use of genetic algorithms to optimize a cooperative learning team. In this research, knowledge structures are constructed by Apriori algorithm.
To verify that the proposed adaptive e-learning guidance system improves the cooperative learning outcomes of students, purposive sampling is used. Experimental samples are obtained from 20 high-school special education students. The experimental group exhibited better mathematical performance and collaborative performance than the control group.

MATERIALS AND METHODS

Heterogeneous grouping
In this work, we regard the grouping problem as an optimizing team problem. The optimizing team problem is one kind of best combination problem. We use the genetic algorithm which can be the best kind of lieutenant colonel algorithm to solve this optimizing team problem.
Learning path planning
This study analyzes the differences between standard knowledge model and learning group knowledge model. According to Ling-Hsiu Chen (2011) proposed misconceptions diagnostic methods, we added the condition threshold filtering method to increase the accuracy of the misconceptions diagnosis method. According to the results of the difference analysis in knowledge model, we use the proposed algorithm to select learning materials according to the misconceptions. Finally, we generate an adaptive learning path for students to learn.

RESULTS AND DISCUSSION

Heterogeneous grouping
According to students learning style score and thinking style score, we use this two scores to generate heterogeneous group. Genetic algorithms are used herein to perform the heterogeneous grouping.

Figure 5.9 Heterogeneous grouping results

Figure 5.9 presents the sum of the deviation from the mean (SDFM) as calculated using genetic algorithm. A minimum SDFM is obtained, representing the best grouping, as shown in Table 5.4.

Table 5.4 Heterogeneous grouping results
Gruop Members
1 16,8,18,14
2 11,4,5,7
3 2,3,17,6
4 13,10,15,19
5 1,9,12,20

CONCLUSION

E-learning represents a new trend. Cooperative learning not only help students to solve problems but also improves their ability to interact with others. This research proposes an adaptive digital technology cooperative learning model for students who require special teaching. The main contributions of this research are adaptive cooperative e-learning guidance, a method for heterogeneously grouping students and a method for planning learning paths. Experimental results revealed that the students who were taught using this system performed better than the control group in mathematics. This work considered only students with mild disabilities, whose bodily functions do not differ from those of the general population, and who can learn to operate a computer. However, many special education students are limited in their ability to use computer hardware and software. Students with special may need hardware with special configurations, and improved user interfaces to support them in digital cooperative learning.

Agrawal, R., & Srikant, R. （1994）. Fast Algorithms for Mining Association Rules in Large Databases. Paper presented at the Proceedings of the 20th International Conference on Very Large Data Bases.
ALGOZZINE, R., Henley, M., & RAMSEY, R. （2005）. Characteristics of and strategies for teaching students with mild disabilities. Recherche, 67, 02.
Bannon, L. J. (1995, January). Issues in computer supported collaborative learning. In Computer supported collaborative learning (pp. 267-281). Springer Berlin Heidelberg.
Bäck, Thomas. （1996）. Evolutionary Algorithms in Theory and Practice, Oxford University Press, New York.
Berry, M.J.A., and Linoff, L. （1997）. “Data Mining Techniques: For Marketing, Sales, and Customer Support,” John Wiley & Sons, Inc.
Badian, N. （1999）. Persistent arithmetic, reading, or arithmetic and reading disability. Annals of Dyslexia, 49（1）, 43-70.
Brusilovsky, P. （2001）. Methods and Technologies of Adaptive Hypermedia. International Journal of User Modeling and User-Adapted Interaction, 11, 87-110.
Borges, M. A. F., & Baranauskas, M. C. C. (2003). CollabSS: A tool to help the facilitator in promoting collaboration among learners. Educational Technology & Society, 6(1), 2003.
Constantino-González, M. D. L. A., & Suthers, D. D. (2002, January). Coaching collaboration in a computer-mediated learning environment. In Proceedings of the Conference on Computer Support for Collaborative Learning: Foundations for a CSCL Community (pp. 583-584). International Society of the Learning Sciences.
Chen, L. H. (2011). Enhancement of student learning performance using personalized diagnosis and remedial learning system. Computers & Education, 56(1), 289-299.
Dunn, R.S., & Dunn, K.J. （1992）. Teaching elementary students through their individual learning styles : practical approaches for grades 3-6. Boston: Allyn and Bacon.
De Bra, P., Brusilovsky, P., & Houben, G. J. （1999）. Adaptive hypermedia: From systems to framework. Acm Computing Surveys, 31, U58-U63.
Dugan, E., Kamps, D., Leonard, B., Watkins, N., Rheinberger, A., & Stackhaus, J. (1995). Effects of cooperative learning groups during social studies for students with autism and fourth‐grade peers. Journal of applied behavior analysis, 28(2), 175-188.
Education and Skills Committee. （2006）. The schools white paper: higher standards, better schools for all. First report of session 2005, 6.
Felder, R.M., & Silverman, L.K. （1988）. Learning and Teaching Styles in Engineering-Education. Engineering Education, 78（7）, 674-681.
Fuchs, L.S., & Fuchs, D. （2001）. Principles for the Prevention and Intervention of Mathematics Difficulties. Learning Disabilities Research & Practice, 16（2）, 85-95.
Gregorc, A.F. （1979）. Learning/teaching styles: Their nature and effects. Student learning styles: Diagnosing and prescribing programs, 19-26.
Gress, C. L., Fior, M., Hadwin, A. F., & Winne, P. H. (2010). Measurement and assessment in computer-supported collaborative learning. Computers in Human Behavior, 26(5), 806-814.
Honey, P., & Mumford, A. （1989）. Learning styles questionnaire: Organization Design and Development, Incorporated, 1989, c1986.
Holland, John H. （1992）. Adaptation in Natural and Artificial Systems, the MIT Press, Cambridge.
Harasim, L. (1999). A framework for online learning: The Virtual-U. Computer, 32(9), 44-49.
Han, J. and Kamber, M. （2001）. “Data Mining : Concepts and Techniques,” Morgan Kaufmann Publishers.
Hong, S. (2005). Nonsingularity of least common multiple matrices on gcd-closed sets. Journal of Number Theory, 113(1), 1-9.
Huang, C. (2012). Discriminant and criterion-related validity of achievement goals in predicting academic achievement: A meta-analysis. Journal of Educational Psychology, 104(1), 48.
Isenhour, P. L., Rosson, M. B., & Carroll, J. M. (2001). Supporting interactive collaboration on the Web with CORK. Interacting with Computers, 13(6), 655-676.
Jenkins, J. R., Antil, L. R., Wayne, S. K., & Vadasy, P. F. (2003). How cooperative learning works for special education and remedial students. Exceptional Children, 69(3), 279-290.
Jackson, A. T., Brummel, B. J., Pollet, C. L., & Greer, D. D. (2013). An evaluation of interactive tabletops in elementary mathematics education. Educational Technology Research and Development, 61(2), 311-332.
Kolb, D.A. （1985）. Learning-Style Inventory: Boston: McBer & Company.
Kleissner, C.（1998）. Data mining for the enterprise, Proceedings of the Hawaii International Conference on System Sciences, 7, 295-304.
Karampiperis, P., & Sampson, D. (2005). Adaptive learning resources sequencing in educational hypermedia systems. Educational Technology & Society, 8(4), 128-147.
Kreijns, K., Vermeulen, M., Kirschner, P. A., Buuren, H. V., & Acker, F. V. (2013). Adopting the Integrative Model of Behaviour Prediction to explain teachers’ willingness to use ICT: a perspective for research on teachers’ ICT usage in pedagogical practices. Technology, Pedagogy and Education, 22(1), 55-71.
Lewis, R.B. （1993）. Special education technology : classroom applications. Pacific Grove, Calif.: Brooks/Cole Pub. Co.
Lopata, C., Miller, K. A., & Miller, R. H. (2003). Survey of actual and preferred use of cooperative learning among exemplar teachers. The journal of educational research, 96(4), 232-239.
Lazakidou, G., & Retalis, S. (2010). Using computer supported collaborative learning strategies for helping students acquire self-regulated problem-solving skills in mathematics. Computers & Education, 54(1), 3-13.
Latham, A, Crockett, K, McLean, D, & Edmonds, B. （2012）. A conversational intelligent tutoring system to automatically predict learning styles. Computers & Education, 59（1）, 95-109.
McLeod, T. M., & Armstrong, S. W. (1982). Learning disabilities in mathematics—skill deficits and remedial approaches at the intermediate and secondary level. Learning Disability Quarterly, 5(3), 305-311.
Mayer, R. E. (1992). Thinking, problem solving, cognition . WH Freeman/Times Books/Henry Holt & Co.
Mitchell, M. (1996). An introduction to genetic algorithms, MIT Press, Cambridge, Massachusetts. Motivation Contemporary Educational Psychology 19,167-178.
Man, K. F., et. al. （1999）. Genetic Algorithms, Springer-Verlag, London.
McMaster, K. N., & Fuchs, D. (2002). Effects of cooperative learning on the academic achievement of students with learning disabilities: An update of Tateyama‐Sniezek’s review. Learning Disabilities Research & Practice, 17(2), 107-117.
Mazzocco, M. M., & Myers, G. F. (2003). Complexities in identifying and defining mathematics learning disability in the primary school-age years. Annals of dyslexia, 53(1), 218-253.
Novak, J. D., & Gowin, D. B. （1984）. Learning how to learn. Cambridge Cambridgeshire ; New York: Cambridge University Press.
Nunnery, J. A., Chappell, S., & Arnold, P. (2013). A Meta-analysis of a Cooperative Learning Models Effects on Student Achievement in Mathematics. Cypriot Journal of Educational Sciences, 8(1), 34-48.
Rovai, A.P. （2000）. Building and sustaining community in asynchronous learning networks. The Internet and higher education, 3（4）, 285-297.
Russell, R., & Lindholm, J. （2003）. Metadata standards for the description of portal users: a review.
Slavin ,R. E.（1985）.Cooperative learning：Applying contact theory in desegregated schools.Joural of Social Issues,43-62.
Sternberg, R. J., & Grigorenko. （1995）. Styles of thinking in the school. European Journal for High Ability. 6, 201- 219.
Scifres, E. L., Gundersen, D. E., & Behara, R. S. (1998). An empirical investigation of electronic groups in the classroom. Journal of Education for Business, 73(4), 247-250.
Saab, N. (2012). Team regulation, regulation of social activities or co-regulation: Different labels for effective regulation of learning in CSCL. Metacognition and Learning, 7(1), 1-6.
Tseng, J.C.R., Chu, H.C., Hwang, G.J., & Tsai, C.C. （2008）. Development of an adaptive learning system with two sources of personalization information. Computers & Education, 51（2）, 776-786.
Walberg, H. J. （1975）. Psychological theories of educational individualization.In H. Talmage （Ed.）, Systems of individualized education. Berkeley, C. A:McCutchan, pp. 15-18.
Williams, J., & Rosenbaum, S.C. （2004）. Learning paths : increase profits by reducing the time it takes for employees to get up-to-speed. San Francisco: Jossey-Bass.
Weinberger, A., & Fischer, F. (2006). A framework to analyze argumentative knowledge construction in computer-supported collaborative learning. Computers & education, 46(1), 71-95.
王華沛、李品蓓. （2002）. 以資訊科技幫助閱讀困難學生突破識字障礙: 回饋.
王翌帆. （2006）. 植基於思考風格的適性化數位教材設計準則之初探-以資料結構課程為例. （碩士）, 國立臺南大學, 台南市.
白如婷. （2006）. 數位學習之適性化學習路徑規劃機制研發. （碩士）, 國立成功大學, 台南市.
朱經明. （1997）. 特殊教育與電腦科技. 台北市: 五南.
朱慧娟. （2009）. 適性化數位合作學習導向之教師專業發展研究－以數學學習困難學生數學教學知識之專業發展為例: 行政院國家科學委員會專題研究成果報告.
何素華.（1996）.國小普通班和啟智班兒童合作學習效果之研究.台北：文景書　　　　　　　　　　　　　　　　局。
吳信翰. （2011）.互動式電子白板融入教學對國中學生數學學習成效影響之研究－以「一元一次方程式」單元為例.國立高雄師範大學數學教學碩士班碩士論文，未出版，高雄市.
呂侑時. （ 2012 ）. 輕度障礙學生四則運算文字題解題表現分析與適性化數位學習成效之研究.（碩士）, 國立臺南大學,台南市.
李建興（2008）。國中學生學習風格與數學學業成就之相關研究(未出版之碩士論文)。國立高雄師範大學，高雄市。
李吳軒. （2010）.電腦支援合作學習對因數概念學習之研究.國立新竹教育大學數位學習科技研究所碩士論文，未出版，新竹市.
林進材. （1999）. 教學研究與發展,台北： 五南圖書出版股份有限公司.
林進材. （2000）. 教學理論與方法,台北: 五南圖書出版股份有限公司.
林生傳. （2000）. 新教學理論與策略.台北：五南圖書出版有限公司
林益源. （2004）. 國小高年級健康與體育合作學習之行動研究. （碩士）, 國立中正大學, 嘉義縣.
林懿文. （2010）. 電腦適性化測驗及適性化補救教學系統之成效. （碩士）, 雲林科技大學, 雲林縣.
林坤燦, 張正芬, & 楊宗仁. （2004）. 自閉症兒童的WISC-III智能組型研究. 26, 127-151.
林清山. （2011）. 心理與教育統計學: 台灣東華書局股份有限公司.
邵淑華. (1997). 在國小數學資源班補救教學之成效研究.
侯禎塘. （2004）. 特殊殊教育需求兒童數學學習困難之特質、教學策略與創意遊戲數學之應用: 台中師範學院特教中心.
施淑如. （2006）. 特殊學生工具箱：300個融合教育的策略.
胡永崇. （2001）. 融合教育意義, 爭議與配合措施. 融合教育論文集. 國立嘉義大學特殊教育中心, 21-40.
計惠卿. （2005）. e-Learning 到台灣：從 2002 到 2005.
高翠霞、蔡崇建. （1999）. 學習風格與教學設計: 教育資料與研究.
許麗霞. （2005）.合作學習對國小普通班智能障礙學生數學學習成效之研究(未出版之碩士論文).國立花蓮師範學院，花蓮市.
張春興. （2003）. 教育心理學-三化取向的理與論實踐.
張正仁. （2005）. 合作學習對國小六年級學生國語文學習成效與同儕互動影響之研究. （碩士）, 屏東科技大學, 屏東縣.
張杏如. (2010). 合作學習的理論基礎. 網路社會學通訊期刊. 第八十六期.
教育部. (2011). 國民教育階段特殊教育課程發展共同原則及課程綱要總綱.
陳心怡、朱建軍、陳榮華. （2000）. WISC-III 分測驗組合之假設解釋與亯度估計。國立臺灣大學特殊教育研究學報，19，1-14.
陳志欣. （2002）. 環境議題教學對國小學童環境認知、態度及行為之影響. （碩士）, 屏東師範學院, 屏東縣.
陳明聰. （2002）. 數位學習環境中身心障礙學生學習的契機、挑戰與因應。在國立嘉義大學特殊教育中心編著，特殊教育教材教法與教學文集 （pp. 129-154）.
陳淑珍. （2005）. 不同學習風格的國小高年級學童使用數位學習系統進行水的三態教學之學習成效探討. （碩士）, 國立新竹教育大學, 新竹市.
陳茂欽. （2008）. 網路教學系統上的獎懲機制與國小學童認知風格對學習成效之影響研究. （碩士）, 大葉大學, 彰化縣.
黃姿慎、孟瑛如. （2008）. 國民中小學學習障礙學生在魏氏兒童智力量表三版 （WISC-Ⅲ） 表現特徵研究. 新竹教育大學學報, 25（1）, 99-125.
黃俊勳. （2012）. 身心障礙學生之適性化數位學習模式研發-以數學學習為例. （碩士）, 成功大學, 台南市.
曾憲雄、蔡秀滿、蘇東興、曾秋蓉、王慶堯. （2005）. 資料探勘 Data Mining. 台北: 旗標出版股份有限公司.
葉道明、李春雄、林鳳釵. (2004). 虛擬合作學習的互動學習模式之探討. 國立屏東師範學院「2004 數位學習研討會」
詹志禹（1998）. 數學焦慮的緣起. 研究, 14, 99-140.
董庭豪（2009）。透過電腦輔助合作學習活動增進國小學童數學估算表現之研究（未出版之碩士論文）。國立新竹教育大學數位學習科技研究所，新竹。
劉湘川、李浚淵、郭伯臣. （2003）. 以知識結構為主的診斷測驗編製及其在補救教學分組之應用─以數學領域五年級因數與倍數為例.九十二學年度師範學院教育學術論文發表會. 2003 年 10 月 24~25日, 台南師範學院.
劉明洲、葉惠雯. （2004）. 植基於學習風格的適性學習系統之探討.
劉耀明. （2007）. 學習風格在數位學習環境中對學習成效及學習態度影響之研究. （碩士）, 國立中正大學, 嘉義縣.
蔡宗武. （2008）. 從工作記憶理論談學習障礙兒童的教學輔導. 27.
鄭博信、詹勳國、劉曼麗、王瑋樺. （2000）. 數學學習障礙學生解題與錯誤類型之研究. 八十九學年度師範學院教育學術論文發表會論文集 （2）（頁 571-596）. 國立新竹師範學院.
賴怡娟. （2009）. 。學習風格與優弱勢能力為基之學習障礙學生適性化數位學習研究—以國小數學乘除法文字題為例. 國立台南大學, 台南市.
鍾斌賢, 林聰武, & 吳育龍. （2001）. 於網際網路上應用概念圖輔助學習之研究: 第五屆全球華人學習科技研討會暨第十屆國際電腦輔助教學研討會.
謝君琳. （2003）. 合作學習對國小四年級數學低成就學生數學學習與同儕互動之影響. （碩士）, 彰化師範大學, 彰化縣.
謝章冠 (2002)，網路學習之學習路徑控制機制(碩士)，國立中山大學資訊管理學系研究所.高雄市。
梁明華, & 曾明基. (2010). 高雄市新興國小無障礙校園環境現況及改善之研究. （碩士）, 國立臺南大學,.
蕭嘉琳, & 黃國禎. （2001）. 互動式概念關係建立輔助系統在學習診斷之應用. 民國 90 年, 6.
蘇怡慈(2012)。電腦支援合作學習應用於國小分數學習之研究。國立新竹教育大學數位學習科技研究所碩士論文。