近年來，MOOC提供廣泛的課程，包括高質量的視頻講座，以世界各地的大學教授所開的專業課程為特色。 這種基於視頻的學習的創新應用引起了教育領域研究人員的關注。 因此，我們實作了一個學生分群分析系統。它會在初始的階段進行了問卷調查，以了解這種課程中學生的學習動機和學習風格，隨後我們會利用分群演算法對之前的課程進行分析，來定義分群組別的種類。換句話說，這項研究的目的是提出一種方法，藉由找到學習動機和學習行為之間的聯繫，使用問卷調查結果和預定義的群體類型在早期對學生進行分群，且隨著課程的進展我們會每日執行了分群分析系統，讓我們分群結果越來越準確。 問卷調查結果能夠提供了初步參考資料，能夠當成學生分群的初步依據，藉此解決冷啟動的問題。 另外，有了更多樣本，我們也可以更好地優化分群組別的定義並添加新的組。 除此之外，我們還將設計一個深度學習的預測模型。 通過預測分群結果，我們可以評估學生可能的學習策略或學習風格。 它的目的是幫助我們的平台更多地了解學生。 藉由學習分析的方式，使我們能夠提供學生更適性化的輔導，藉此提高學生的完課率。

Massive open online courses (MOOCs) offer a wide range of courses and include high-quality video lectures that feature professors from universities across the world. Such innovative use of video-based learning has attracted attention from researchers and practitioners in the education field. Therefore, we conducted questionnaire surveys to detect student learning motivations and learning styles during such a course. The purpose of this study is to propose a method that can use questionnaire results and predefined group types to classify students in the early stages to deal with the cold-start problem. We found a link between learning motivation and learning behavior. As the class progressed, we executed a daily clustering system which was implemented using k-means method. The questionnaire results provided a preliminary reference, which forms the basis for student grouping. With a greater sample, we could also better optimize the definition of groups and add new groups. In addition, we also design a prediction model for deep learning. By predicting the clustering results, we could estimate students’ possible learning strategies or learning styles enabling creators of MOOC platforms to learn more about the students and provide more help and counseling to improve student completion.

[1] H.-H. Hsu, N.-F. Huang, S.-C. Chen, C.-A. Lee, and J.-W. Tzeng, “Misconceptions mining and visualizations for chinese-based moocs forum based on nlp,” in Big Data Analysis (ICBDA), 2017 IEEE 2nd International Conference on. IEEE, 2017, pp. 634–639.
[2] N.-F. Huang, H.-H. Hsu, S.-C. Chen, C.-A. Lee, Y.-W. Huang, P.-W. Ou, and J.-W. Tzeng, “Videomark: A video-based learning analytic technique for moocs,” in Big Data Analysis (ICBDA), 2017 IEEE 2nd International Conference on. IEEE, 2017, pp. 753–757.
[3] R. Kop, “The challenges to connectivist learning on open online networks: Learning experiences during a massive open online course,” The International Review of Research in Open and Distributed Learning, vol. 12, no. 3, pp. 19–38, 2011.
[4] G. Veletsianos and P. Shepherdson, “A systematic analysis and synthesis of the empirical mooc literature published in 2013–2015,” The International Review of Research in Open and Distributed Learning, vol. 17, no. 2, 2016.
[5] J. DeBoer, G. S. Stump, D. Seaton, and L. Breslow, “Diversity in mooc students’backgrounds and behaviors in relationship to performance in 6.002 x,” in Proceedings of the Sixth Learning International Networks Consortium Conference, vol. 4, 2013, pp. 16–19.
[6] K. F. Hew and W. S. Cheung, “Students’and instructors’use of massive open online courses (moocs): Motivations and challenges,” Educational research review, vol. 12, pp. 45–58, 2014.
[7] P. d. Barba, G. E. Kennedy, and M. Ainley, “The role of students’ motivation and participation in predicting performance in a mooc,” Journal of Computer Assisted Learning, vol. 32, no. 3, pp. 218–231, 2016.
[8] C. Gütl, R. H. Rizzardini, V. Chang, and M. Morales, “Attrition in mooc: Lessons learned from drop-out students,” in International Workshop on Learning Technology for Education in Cloud. Springer, 2014, pp. 37–48.
[9] A. I. Schein, A. Popescul, L. H. Ungar, and D. M. Pennock, “Methods and metrics for cold-start recommendations,” in Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval. ACM, 2002, pp. 253–260.
[10] D. Gasevic, V. Kovanovic, S. Joksimovic, and G. Siemens, “Where is research on massive open online courses headed? a data analysis of the mooc research initiative,” The International Review of Research in Open and Distributed Learning, vol. 15, no. 5, 2014.
[11] H. Hayati, J. S. Tahiri, M. K. Idrissi, and S. Bennani, “Classification system of learners engagement within massive open online courses,” in Information Science and Technology (CiSt), 2016 4th IEEE International Colloquium on. IEEE, 2016, pp. 527–530.
[12] R. L. Rodrigues, J. L. C. Ramos, J. C. S. Silva, and A. S. Gomes, “Discovery engagement patterns moocs through cluster analysis,” IEEE Latin America Transactions, vol. 14, no. 9, pp. 4129–4135, 2016.
[13] A. Ng and D. Koller, “Coursera,” Retrieved May 20, 2018, from the World Wide Web: https://zh-tw.coursera.org/, 2012.
[14] M. I. of Technology and H. University, “edx,” Retrieved May 20, 2018, from the World Wide Web: https://www.edx.org/, 2012.
[15] National Tsing-Hua University, “Sharecourse,” Retrieved May 20, 2018, from the World Wide Web: http://www.sharecourse.net/sharecourse/, 2012.
[16] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” nature, vol. 521, no. 7553, p. 436, 2015.
[17] I. Goodfellow, Y. Bengio, A. Courville, and Y. Bengio, Deep learning. MIT press Cambridge, 2016, vol. 1.
[18] J. Schmidhuber, “Deep learning in neural networks: An overview,” Neural networks, vol. 61, pp. 85–117, 2015.
[19] M. Leshno, V. Y. Lin, A. Pinkus, and S. Schocken, “Multilayer feedforward networks with a non-polynomial activation function can approximate any function,” 1992.
[20] G. Cybenko, “Approximation by superpositions of a sigmoidal function,” Mathematics of control, signals and systems, vol. 2, no. 4, pp. 303–314, 1989.
[21] V. Nair and G. E. Hinton, “Rectified linear units improve restricted boltzmann machines,” in Proceedings of the 27th international conference on machine learning (ICML-10), 2010, pp. 807–814.
[22] J. Rafferty, P. Shellito, N. H. Hyman, W. D. Buie et al., “Practice parameters for sigmoid diverticulitis,” Diseases of the colon & rectum, vol. 49, no. 7, pp. 939–944, 2006.
[23] M. R. Anderberg, “Cluster analysis for applications,” Office of the Assistant for Study Support Kirtland AFB N MEX, Tech. Rep., 1973.
[24] I. H. Witten, E. Frank, M. A. Hall, and C. J. Pal, Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann, 2016.
[25] T. Hastie, R. Tibshirani, and J. Friedman, “Unsupervised learning,” in The elements of statistical learning. Springer, 2009, pp. 485–585.
[26] X. Yang, H. Fu, H. Zha, and J. Barlow, “Semi-supervised nonlinear dimensionality reduction,” in Proceedings of the 23rd international conference on Machine learning. ACM, 2006, pp. 1065–1072.
[27] A. Koutropoulos, M. S. Gallagher, S. C. Abajian, I. de Waard, R. J. Hogue, N. O. Keskin, and C. O. Rodriguez, “Emotive vocabulary in moocs: Context & participant retention.” European Journal of Open, Distance and E-Learning, 2012.
[28] R. F. Kizilcec, C. Piech, and E. Schneider, “Deconstructing disengagement: analyzing learner subpopulations in massive open online courses,” in Proceed-ings of the third international conference on learning analytics and knowledge. ACM, 2013, pp. 170–179.
[29] P. Hill, “Emerging student patterns in moocs: A (revised) graphical view,” WordPress, e-Literate, vol. 10, 2013.
[30] M. Khalil and M. Ebner, “Clustering patterns of engagement in massive open online courses (moocs): the use of learning analytics to reveal student categories,” Journal of computing in higher education, vol. 29, no. 1, pp. 114–132, 2017.
[31] L. Elton, “Strategies to enhance student motivation: a conceptual analysis,” Studies in Higher Education, vol. 21, no. 1, pp. 57–68, 1996.
[32] “Scikit-learn standardscaler,” Retrieved June 27, 2018, from the World Wide Web: http://scikit-learn.org/stable/modules/generated/sklearn. preprocessing.StandardScaler.html.
[33] J. MacQueen, “Some methods for classification and analysis of multivariate observations,” in Proc. Fifth Berkeley Symp. Math. Stat. Probab. Vol. 1 Stat. Berkeley, Calif.: University of California Press, 1967, pp. 281–297. [Online]. Available: http://projecteuclid.org/euclid.bsmsp/1200512992
[34] D. Arthur and S. Vassilvitskii, “K-means++: The Advantages of Careful Seeding,” in Proc. Eighteenth Annu. ACM-SIAM Symp. Discret. Algorithms, ser. SODA ’07. Philadelphia, PA, USA: Society for Industrial and Applied Mathematics, 2007, pp. 1027–1035. [Online]. Available: http://dl.acm.org/citation.cfm?id=1283383.1283494
[35] H. He and E. A. Garcia, “Learning from imbalanced data,” IEEE Transactions on knowledge and data engineering, vol. 21, no. 9, pp. 1263–1284, 2009.
[36] N. V. Chawla, N. Japkowicz, and A. Kotcz, “Special issue on learning from imbalanced data sets,” ACM Sigkdd Explorations Newsletter, vol. 6, no. 1, pp. 1–6, 2004.
[37] H. Han, W.-Y. Wang, and B.-H. Mao, “Borderline-smote: a new oversampling method in imbalanced data sets learning,” in International Conference on Intelligent Computing. Springer, 2005, pp. 878–887.
[38] Y. Zhang, “Severity analysis in motor vehicle crashes in the state of iowa using multiple machine learning and data balancing techniques,” Ph.D. dissertation, State University of New York at Binghamton, 2017.
[39] A. Estabrooks, T. Jo, and N. Japkowicz, “A multiple resampling method for learning from imbalanced data sets,” Computational intelligence, vol. 20, no. 1, pp. 18–36, 2004.
[40] Y. Sun, M. S. Kamel, A. K. Wong, and Y. Wang, “Cost-sensitive boosting for classification of imbalanced data,” Pattern Recognition, vol. 40, no. 12, pp. 3358–3378, 2007.
[41] M. W. Gardner and S. Dorling, “Artificial neural networks (the multilayer perceptron)— a review of applications in the atmospheric sciences,” Atmospheric environment, vol. 32, no. 14-15, pp. 2627–2636, 1998.
[42] R. Kruse, C. Borgelt, F. Klawonn, C. Moewes, M. Steinbrecher, and P. Held, “Multi-layer perceptrons,” in Computational Intelligence. Springer, 2013, pp. 47–81.
[43] B. Lin and A. R. Newton, “Synthesis of multiple level logic from symbolic high-level description languages,” in Proceedings of the International Conference on VLSI, vol. 187. Munich, 1989, p. 196.
[44] F. Chollet, “Keras,” Retrieved June 27, 2018, from the World Wide Web: https://keras.io/, 2015.
[45] R. Kohavi et al., “A study of cross-validation and bootstrap for accuracy estimation and model selection,” in Ijcai, vol. 14, no. 2. Montreal, Canada, 1995, pp. 1137–1145.
[46] N. Magen-Nagar and L. Cohen, “Learning strategies as a mediator for motivation and a sense of achievement among students who study in moocs,” Education and Information Technologies, vol. 22, no. 3, pp. 1271–1290, 2017.
[47] R. F. Kizilcec, M. Pérez-Sanagustín, and J. J. Maldonado, “Self-regulated learning strategies predict learner behavior and goal attainment in massive open online courses,” Computers & Education, vol. 104, pp. 18–33, 2017.
[48] H.-C. Chen, “Questionnaire data set,” Retrieved June 30, 2018, from the World Wide Web: https://goo.gl/1pYXTL, 2018.
[49] National Tsing-Hua University, “Fundamental course of national tsinghua university,” Retrieved June 27, 2018, from the World Wide Web: http://www.sharecourse. net/sharecourse/unit/nthuap, 2018.