磨課師(MOOC)的出現增加了學生學習知識的可能性。伴隨著開放式課程素材，學生擁有非常大的彈性來安排、調整自身的學習方式。而開放式課程素材並非只影響學生的學習，同時也給予課程講師充分的空間來安排課程內容及素材的編排、使用。這樣的彈性造就了MOOC課程的多樣性，例如課程沒有練習題或課程沒有考試。而這樣的彈性會造成學生無法在學習過程中檢視自己的學習成果。為此，我們分析MOOC課程主要的學習方式，觀看課程影片，來預測學生的學習成效，並回饋給學生，讓學生作出自適化的調整。我們透過收集學生觀看影片時的動作資料以及動作發生的時間點，根據間隔效應進行分析，分為學習行為分析與學習活躍度分析兩個類別。然後，利用深度學習的方式，去預測該學生於該學習模式下的學習成效，課程分數與課程等第。最後，系統會將分析數據視覺化成三種圖表，每日學習時間長條圖、每周學習熱點圖、活躍度雷達圖，並將圖表與預測結果反饋給學生，讓學生得以得知目前的學習狀況並加以調整自己的學習方式。

The emergence of massive open online courses(MOOC) increases the possibility of students learning. With the open course materials, students have great flexibility to arrange and adjust their own learning methods. The open course materials not only affect the students' learning, but also give the course instructors sufficient space to arrange the course content and materials. This flexibility has created a diversity of MOOC courses, such as courses without exercises or without exams. It may prevent students from reviewing their learning effectiveness during the learning process. To this end, we analyze the main learning methods of MOOC, video watching, to predict students' learning performance, and give back to students, so that students can make adaptive adjustments. We used the learning logs of videos, analyze them according to the spacing effect, and divide them into two categories: learning behavior analysis and learning activity analysis. Then, use the method of deep learning to predict the student's learning performance, course score and course grade. Finally, the system will visualize the analysis data into three charts, daily learning time bar chart, weekly learning heat map, learning radar chart, and feed back the charts and prediction results to the students, so that the students can learn the current learning status and adjust their learning methods.

Chapter 1 Introduction 1
Chapter 2 Background and Related Works 4
Chapter 3 System Architecture 13
Chapter 4 System Implementation 24
Chapter 5 Experiment and Result 50
Chapter 6 Conclusion and Future Work 54
Bibliography 56

[1] A. Ng and D. Koller, “Coursera,” Retrieved June 29, 2018, from the World Wide Web:https://zh-tw.coursera.org, 2012.
[2] M. I. of Technology and H. University, “edx,” Retrieved June 29, 2018, from the World Wide Web:https://www.edx.org, 2012.
[3] S. Thrun, D. Stavens, and M. Sokolsky, “Udacity,” Retrieved June 29, 2018,from the World Wide Web:https://www.udacity.com, 2012.
[4] M. Khalil and J. Wong, “The essence of time: Taking a look at learning sessions in moocs,” in 2018 Learning With MOOCS (LWMOOCS), 2018, pp.131–133.
[5] Y. Lee, “Effect of uninterrupted time-on-task on students’success in massive open online courses (moocs),”Computers in Human Behavior, vol. 86, pp.174–180, 2018. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0747563218302073
[6] D. Sun, Y. Mao, J. Du, P. Xu, Q. Zheng, and H. Sun, “Deep learning for dropout prediction in moocs,” in 2019 Eighth International Conference on Educational Innovation through Technology (EITT), 2019, pp. 87–90.
[7] N. T. University, “Sharecourse,” Retrieved April 16, 2017, from the World Wide Web:https://www.sharecourse.net/sharecourse/, 2012.
[8] ——, “NTHU cloud,” Retrieved April 16, 2020, from the World WideWeb:https://mooc.nthu.edu.tw/, 2020.
[9] S. M. North, R. Richardson, and M. M. North, “To adapt moocs, or not?that is no longer the question.”Universal Journal of Educational Research,vol. 2, no. 1, pp. 69–72, 2014.
[10] Y. Chengjie, “Challenges and changes of mooc to traditional classroom teaching mode,”Canadian Social Science, vol. 11, no. 1, pp. 135–139, 2015.
[11] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,”nature, vol. 521, no.7553, pp. 436–444, 2015.
[12] I. Goodfellow, Y. Bengio, and A. Courville,Deep Learning. MIT Press, 2016,vol. 4, http://www.deeplearningbook.org.
[13] J. Schmidhuber, “Deep learning in neural networks: An overview,”Neural Networks, vol. 61, pp. 85–117, 2015. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0893608014002135[14] J. Han and C. Moraga, “The influence of the sigmoid function parameters on the speed of back propagation learning,” in From Natural to Artificial Neural Computation. Springer, 1995, pp. 195–201.
[15] K. He, X. Zhang, S. Ren, and J. Sun, “Delving deep into rectifiers: Surpassing human-level performance on image net classification,” in Proceedings of the IEEE international conference on computer vision, dec 2015, pp. 1026–1034.
[16] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,”nature, vol. 323, no. 6088, pp. 533–536, 1986.
[17] M. M. Ashenafi, G. Riccardi, and M. Ronchetti, “Predicting students’ final exam scores from their course activities,” in 2015 IEEE Frontiers in Education Conference (FIE), October 2015, pp. 1–9.
[18] N. Huang, C. Chen, J. Tzeng, T. T. Fang, and C. Lee, “Concept assessment system integrated with a knowledge map using deep learning,” in 2018 Learning With MOOCS (LWMOOCS), September 2018, pp. 113–116.
[19] X. Li, L. Xie, and H. Wang, “Grade prediction in moocs,” in Computational Science and Engineering (CSE) and IEEE Intl Conference on Embedded and Ubiquitous Computing (EUC) and 15th Intl Symposium on Distributed Computing and Applications for Business Engineering (DCABES), 2016 IEEE Intl Conference on. IEEE, 2016, pp. 386–392.
[20] G. van Rossum, “Mongodb,” Retrieved June 29, 2018, from the World Wide Web:www.mongodb.com, 2009.
[21] T. Sinha, P. Jermann, N. Li, and P. Dillenbourg, “Your click decides your fate: Inferring information processing and attrition behavior from mooc video clickstream interactions,”arXiv preprint arXiv:1407.7131, 2014.
[22] F. Chollet, “Keras,” Retrieved June 29, 2018, from the World WideWeb:https://keras.io/, 2015.
[23] G. van Rossum, “Python,” Retrieved June 29, 2018, from the World Wide Web:www.python.org, 1990.
[24] Google Brain Team, “Tensorflow,” Retrieved June 29, 2018, from the World Wide Web:https://github.com/tensorflow/tensorflow, 2015.[25] M. Gardner and S. Dorling, “Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences,”Atmospheric Environment, vol. 32, no. 14, pp. 2627 – 2636, 1998. [Online]. Available:http://www.sciencedirect.com/science/article/pii/S1352231097004470
[26] R. Kruse, C. Borgelt, F. Klawonn, C. Moewes, M. Steinbrecher, and P. Held,MultiLayer Perceptrons, 01 2013, pp. 47–81.
[27] National Tsinghua University, “Introduction to computer networks,” Retrieved September 10, 2018, from the World Wide Web:http://www.sharecourse.net/sharecourse/course/view/courseInfo/1620, 2018.
[28] ——, “Introduction to computer networks,” Retrieved September 18, 2017,from the World Wide Web:http://www.sharecourse.net/sharecourse/course/view/courseInfo/1246, 2017.
[29] ——, “Introduction to computer networks,” Retrieved September 9, 2019,from the World Wide Web:http://www.sharecourse.net/sharecourse/course/view/courseInfo/1907, 2019.
[30] ——, “Introduction to iot,” Retrieved September 18, 2017, from the World Wide Web:http://www.sharecourse.net/sharecourse/course/view/courseInfo/1247, 2017.
[31] ——, “Introduction to iot,” Retrieved February 18, 2019, from the World Wide Web:http://www.sharecourse.net/sharecourse/course/view/courseInfo/1689, 2019.
[32] ——, “Introduction to iot,” Retrieved March 2, 2020, from the World Wide Web:http://www.sharecourse.net/sharecourse/course/view/courseInfo/2102,2020.
[33] ——, “Topics on investment,” Retrieved November 14, 2017, from the World Wide Web:http://www.sharecourse.net/sharecourse/course/view/courseInfo/987, 2017.
[34] ——, “Topics on investment (spring),” Retrieved February 20, 2017, from the World Wide Web:http://www.sharecourse.net/sharecourse/course/view/courseInfo/1026, 2017.
[35] ——, “Topics on investment,” Retrieved February 18, 2019, from the World Wide Web:http://www.sharecourse.net/sharecourse/course/view/courseInfo/1691, 2019.
[36] ——, “Introduction to computer networks,” Retrieved April 25, 2016, from the World Wide Web:http://www.sharecourse.net/sharecourse/course/view/courseInfo/848, 2016.
[37] ——, “Internet security,” Retrieved November 13, 2017, from the World Wide Web:http://www.sharecourse.net/sharecourse/course/view/courseInfo/1329,2017.
[38] S. M. Kendall, “Rank correlation,”Van Nostrand’s Scientific Encyclopedia,2005.
[39] W. T. Lin and A. R. Newton, “Newton: synthesis of multiple-level logic from symbolic high-level description languages,” August 1989.
[40] A. Ronacher, “Flask,” Retrieved June 29, 2018, from the World Wide Web:https://github.com/pallets/flask, 2010.
[41] National Tsinghua University, “Introduction to calculus (i),” Retrieved May 1, 2020, from the World Wide Web:https://mooc.nthu.edu.tw/cid=10900MATH0001, 2020.