大型線上開放課程（MOOCs）在近年來的蓬勃發展，讓來自世界各地的使用者能夠不受地區和時間的限制，增加學習的機會。
然而由於線上過多複雜的資源，漸漸地讓使用者迷失在如何找尋適當的學習教材。
還有在課程裡的學習中遇到困難時，也需要有一個能夠提供學習策略以及知識和訊息管理角色。 在此篇論文裡，我們提出並且實作出了一個基於學習診斷結合推薦系統的磨課師智慧助教。推薦的素材有兩種，第一種是課程的推薦，這個部分我們先算出學生對於課程的隱性反饋評分後，再應用了貝氏個人化排序(BPR, Bayesian Personalized Ranking)的演算法來對進行課程推薦模組的訓練；第二種是分析學習助手模組的學生學習診斷與分群結果，來對不同知識背景和不同學習能力的學生，做出所適合他們的課程素材(影片、練習題)的推薦。在實驗與驗證的部分，也分成兩個方法來實作。對於課程推薦模組，我們利用了AUC ROC Score來進行模組訓練完過後的評估，並且得到0.75左右的高分，表示此課程推薦模組有一定水準的準確度。第二個部分我們請學生協助填寫線上的問卷，問卷的回應有一半以上的回應都是正面的，表明這個系統對於學生的學習上是有一定程度的幫助的。所有想法與實作步驟會，在接下來的章節內容詳細介紹。

The rapid development of Massive open on-line courses (MOOCs) in recent years has enabled users from all over the world to increase their chances to learn on-line without being affected by the region and without time constraints.
However, due to too many complicated resources on the line, users are often overwhelmed by this massive resources and cannot find suitable learning materials.
In addition, when students encounter difficulties in the course of learning, they also need an assistant role who can be able to provide learning strategies as well as knowledge and message management.
In this study, we proposed and implemented a MOOC intelligent recommendation system, short for MOOCIRS, based on learning diagnosis and recommendation system.
There are two kinds of recommended materials.
The first one is the recommendation of the course. In this part, we first calculate the students' implicit feedback scores for the course, and then apply the algorithm of Bayesian Personalized Ranking (BPR) to train the course recommendation module;
The second one is by analyzing the student's learning diagnosis and clustering results from the learning assistant module to make personalized course materials recommendations (videos, exercises) to the students with different knowledge backgrounds and different learning abilities.
In the experiment and evaluation part, it is also divided into two methods to implement.
For the course recommendation module, we used the AUC ROC Score to perform the evaluation after the module is trained, and got a high score of about 0.75, indicating that the recommended module of this course has a certain level of accuracy and reliability.
In the second part, we asked the students to assist in filling the on-line questionnaire. More than half of the responses to the questionnaire were positive ,indicating that the system we proposed has a certain degree of help in student learning.
The overall ideas and practical steps will be described in detail in the following chapters.

Introduction ......1
Related Works ......4
System Architecture ......14
System Implementation ......22
Experiment ......38
Conclusion and Future Work ......48

[1] L. Breslow, D. Pritchard, J. DeBoer, G. Stump, A. D. Ho, and D. Seaton, “Studying learning in the worldwide classroom: Research into edx’s first mooc,” 06 2013.

[2] N. F. Huang, H. H. Hsu, S. C. Chen, C. A. Lee, Y. W. Huang, P. W. Ou, J. W. Tzeng, and H. H. Hsu, “Videomark: A video-based learning analytic technique for moocs,” in 2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA)(, March 2017, pp. 753–757.

[3] D. T. Seaton, Y. Bergner, I. Chuang, P. Mitros, and D. E. Pritchard, “Who does what in a massive open online course?” Commun. ACM, vol. 57, no. 4, pp. 58–65, Apr. 2014. [Online]. Available: http://doi.acm.org/10.1145/2500876

[4] M. Wang, J. Peng, B. Cheng, H. Zhou, and J. Liu, “Knowledge visualization for self-regulated learning.” Educational Technology & Society, vol. 14, no. 3, pp. 28–42, 2011.

[5] J. A. Ruipérez-Valiente, P. J. Muñoz-Merino, C. D. Kloos, K. Niemann, M. Scheffel, and M. Wolpers, “Analyzing the impact of using optional activities in self-regulated learning,” IEEE Transactions on Learning Technologies, vol. 9, no. 3, pp. 231–243, 2016.
[6] A. Sunar, S. White, N. Abdullah, and H. Davis, “How learners’interactions
sustain engagement: a mooc case study,” IEEE Transactions on Learning
Technologies, 2016.

[7] P. Goodyear and S. Retalis, “Technology-enhanced learning,” Rotterdam:
Sense Publishers, 2010.

[8] A. Kirkwood and L. Price, “Technology-enhanced learning and teaching in
higher education: what is ‘enhanced’and how do we know? a critical
literature review,” Learning, Media and Technology, vol. 39, no. 1, pp. 6–36,
2014. [Online]. Available: https://doi.org/10.1080/17439884.2013.770404

[9] F. Ricci, L. Rokach, and B. Shapira, Introduction to Recommender Systems
Handbook. Boston, MA: Springer US, 2011, pp. 1–35. [Online]. Available:
https://doi.org/10.1007/978-0-387-85820-3_1

[10] F. Isinkaye, Y. Folajimi, and B. Ojokoh, “Recommendation systems:
Principles, methods and evaluation,” Egyptian Informatics Journal,
vol. 16, no. 3, pp. 261 – 273, 2015. [Online]. Available: http:
//www.sciencedirect.com/science/article/pii/S1110866515000341

[11] D. H. Park, H. K. Kim, I. Y. Choi, and J. K. Kim, “A literature review and classification of recommender systems research,” Expert Systems with Applications, vol. 39, no. 11, pp. 10 059 – 10 072, 2012. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0957417412002825

[12] A. Klašnja-Milićević, M. Ivanović, and A. Nanopoulos, “Recommender systems in e-learning environments: a survey of the state-of-the-art and possible extensions,” Artificial Intelligence Review, vol. 44, no. 4, pp. 571–604, Dec 2015. [Online]. Available: https://doi.org/10.1007/s10462-015-9440-z

[13] R. M. Felder and L. K. Silverman, “Learning and teaching styles in engineering education,” ENGINEERING EDUCATION, 1988.

[14] F. Bousbahi and H. Chorfi, “Mooc-rec: A case based recommender system for moocs,” Procedia - Social and Behavioral Sciences, vol. 195, pp. 1813 – 1822, 2015, world Conference on Technology, Innovation and Entrepreneurship. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S1877042815038744

[15] J. L. Kolodner, “An introduction to case-based reasoning,” Artificial Intelligence Review, vol. 6, no. 1, pp. 3–34, Mar 1992. [Online]. Available: https://doi.org/10.1007/BF00155578

[16] M. I. of Technology and H. University, “edx,” Retrieved May 16, 2018, from the World Wide Web: https://www.edx.org/, 2012.

[17] T. University, “Xuetangx,” Retrieved May 16, 2018, from the World Wide Web: http://www.xuetangx.com/, 2013.

[18] M. I. of Technology and H. University, “openedx,” Retrieved June 15, 2018, from the World Wide Web: https://open.edx.org, 2012.

[19] N. T. University, “Sharecourse,” Retrieved May 15, 2018, from the World Wide Web: http://www.sharecourse.net/sharecourse/, 2012.

[20] Y.-C. CHENG, J.-W. TZENG, N.-F. HUANG, C.-A. LEE, and M.-L. Kuo, “Development of alternative conception diagnostic system based on item response theory in moocs,” in Proceedings of the 25th International Conference on Computers in Education (ICCE 2017). New Zealand: Asia-Pacific Society for Computers in Education, 2017, pp. 469 – 474.

[21] H. M. Chang, T. M. L. Kuo, S. C. Chen, C. A. Li, Y. W. Huang, Y. C. Cheng, H. H. Hsu, N. F. Huang, and J. W. Tzeng, “Developing a data-driven learning interest recommendation system to promoting self-paced learning on moocs,” in 2016 IEEE 16th International Conference on Advanced Learning Technologies (ICALT), July 2016, pp. 23–25.

[22] N.-F. Huang, C.-A. Lee, Y.-W. Huang, P.-W. Ou, H.-H. Hsu, S.-C. Chen, and J.-W. Tzengßer, “On the automatic construction of knowledge-map from handouts for mooc courses,” in Advances in Intelligent Information Hiding and Multimedia Signal Processing, J.-S. Pan, P.-W. Tsai, J. Watada, and L. C. Jain, Eds. Cham: Springer International Publishing, 2018, pp. 107–114.

[23] A. Ng and D. Koller, “Coursera,” Retrieved April 16, 2018, from the World Wide Web: https://zh-tw.coursera.org/, 2012.

[24] S. University, “Uooc,” Retrieved May 17, 2018, from the World Wide Web: http://www.uooconline.com/misc/about/, 2013.

[25] “Small private online course,” Retrieved May 21, 2018, from the World Wide Web: https://en.wikipedia.org/wiki/Small_private_online_course.

[26] G. Adomavicius and A. Tuzhilin, “Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions,” IEEE Transactions on Knowledge and Data Engineering, vol. 17, no. 6, pp. 734–749, June 2005.

[27] P. Lops, M. de Gemmis, and G. Semeraro, Content-based Recommender Systems: State of the Art and Trends. Boston, MA: Springer US, 2011, pp. 73–105. [Online]. Available: https://doi.org/10.1007/978-0-387-85820-3_3

[28] P. Resnick, N. Iacovou, M. Suchak, P. Bergstrom, and J. Riedl, “Grouplens: An open architecture for collaborative filtering of netnews,” in Proceedings of the 1994 ACM Conference on Computer Supported Cooperative Work, ser. CSCW ’94. New York, NY, USA: ACM, 1994, pp. 175–186. [Online]. Available: http://doi.acm.org/10.1145/192844.192905

[29] J. L. Herlocker, J. A. Konstan, A. Borchers, and J. Riedl, “An algorithmic framework for performing collaborative filtering,” SIGIR Forum, vol. 51, no. 2, pp. 227–234, Aug. 2017. [Online]. Available: http://doi.acm.org/10.1145/3130348.3130372

[30] X. Su and T. M. Khoshgoftaar, “A survey of collaborative filtering techniques,” Adv. in Artif. Intell., vol. 2009, pp. 4:2–4:2, Jan. 2009. [Online]. Available: http://dx.doi.org/10.1155/2009/421425

[31] J.-H. Liu, T. Zhou, Z.-K. Zhang, Z. Yang, C. Liu, and W.-M. Li, “Promoting cold-start items in recommender systems,” PLOS ONE, vol. 9, no. 12, pp. 1–13, 12 2014. [Online]. Available: https://doi.org/10.1371/journal.pone.0113457

[32] 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, ser. SIGIR ’02. New York, NY, USA: ACM, 2002, pp. 253–260. [Online]. Available: http://doi.acm.org/10.1145/564376.564421

[33] Y. Koren, R. Bell, and C. Volinsky, “Matrix factorization techniques for recommender systems,” Computer, vol. 42, no. 8, pp. 30–37, Aug 2009.

[34] S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme, “BPR:bayesian personalized ranking from implicit feedback,” CoRR, vol. abs/1205.2618, 2012. [Online]. Available: http://arxiv.org/abs/1205.2618

[35] D. W. Oard, J. Kim et al., “Implicit feedback for recommender systems,” in Proceedings of the AAAI workshop on recommender systems, vol. 83. WoUongong, 1998.

[36] “Maximum a posteriori estimation,” Retrieved May 7, 2018, from the World Wide Web: https://en.wikipedia.org/wiki/Maximum_a_posteriori_estimation.

[37] J. H. Friedman, “Stochastic gradient boosting,” Computational Statistics & Data Analysis, vol. 38, no. 4, pp. 367–378, 2002.

[38] N.-F. Huang, C.-C. Chen, J.-W. Tzeng, and C.-A. Lee, “Concept assessment system integrated with knowledge map using deep learning,” IEEE Learning with MOOCs V: MOOCs for ALL - A Social and International Approach, LWMOOCS V, September 2018.

[39] N.-F. Huang, I.-H. Hsu, C.-A. Lee, H.-C. Chen, J.-W. Tzeng, and T.-T. Fang, “The clustering analysis system based on students’motivation and learning behavior,” IEEE Learning with MOOCs V: MOOCs for ALL - A Social and International Approach, LWMOOCS V, September 2018.

[40] Y. Li and H. Li, “Mooc-frs: A new fusion recommender system for moocs,” in 2017 IEEE 2nd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), March 2017, pp. 1481–1488.

[41] M. Kula, “Metadata embeddings for user and item cold-start recommendations,” in Proceedings of the 2nd Workshop on New Trends on Content-Based Recommender Systems co-located with 9th ACM Conference on Recommender Systems (RecSys 2015), Vienna, Austria, September 16-20, 2015., ser. CEUR Workshop Proceedings, T. Bogers and M. Koolen, Eds., vol. 1448. CEUR-WS.org, 2015, pp. 14–21. [Online]. Available: http://ceur-ws.org/Vol-1448/paper4.pdf

[42] J. Weston, S. Bengio, and N. Usunier, “Wsabie: Scaling up to large vocabulary image annotation,” in Proceedings of the International Joint Conference on Artificial Intelligence, IJCAI, 2011.

[43] A. R. M. D. Lord, A. Mönnich, “Flask,” Retrieved May 20, 2018, from the World Wide Web:http://flask.pocoo.org/docs/1.0/.

[44] “Wsgi,” Retrieved May 2, 2018, from the World Wide Web: https://en.wikipedia.org/wiki/Web_Server_Gateway_Interface.

[45] A. Ronacher, “Jinjia2,” Retrieved May 2, 2018, from the World Wide Web: http://jinja.pocoo.org/docs/2.10/.

[46] “uwsgi,” Retrieved May 7, 2018, from the World Wide Web: https://en.wikipedia.org/wiki/UWSGI.

[47] W. Reese, “Nginx: the high-performance web server and reverse proxy,” Linux Journal, vol. 2008, no. 173, p. 2, 2008.

[48] B. B. et al., “Apache,” Retrieved May 2, 2018, from the World Wide Web:http://jinja.pocoo.org/docs/2.10/.

[49] “Receiver operating characteristic,” Retrieved May 7, 2018, from the World Wide Web: https://en.wikipedia.org/wiki/Receiver_operating_characteristic.

[50] G. Schröder and et al., “Setting goals and choosing metrics for recommender system evaluations.”

[51] “Confusion matrix,” Retrieved May 2, 2018, from the World Wide Web: https://en.wikipedia.org/wiki/Confusion_matrix.

[52] Y. K. Dwivedi, N. P. Rana, A. Jeyaraj, M. Clement, and M. D. Williams, “Re-examining the unified theory of acceptance and use of technology (utaut): Towards a revised theoretical model,” Information Systems Frontiers, pp. 1– 16, 2017.

[53] M. Tavakol and R. Dennick, “Making sense of cronbach’s alpha,” International journal of medical education, vol. 2, p. 53, 2011.

[54] J. A. Gliem and R. R. Gliem, “Calculating, interpreting, and reporting cronbach’s alpha reliability coefficient for likert-type scales.” Midwest Researchto-Practice Conference in Adult, Continuing, and Community Education, 2003.

[55] J. Jovanovic, D. Gasevic, and V. Devedzic, “Tangram for personalized learning using the semantic web technologies,” vol. 1, 08 2009.

[56] C. G. G., “Natural language processing,” Annual Review of Information Science and Technology, vol. 37, no. 1, pp. 51–89. [Online]. Available:
https://onlinelibrary.wiley.com/doi/abs/10.1002/aris.1440370103