近年來大型線上開放課程（MOOCs）為來自世界各地的使用者帶來學習的機會， 然而線上課程使許多使用者面臨認知超載以及概念和導航障礙。尤其是在學習中遇到困難時，需要有效的學習策略以及知識和訊息的管理。
在此篇論文裡，我們使用課程講義來自動產生線上課程的知識圖。
我們認為線上課程講義是來自教師所創造的課程概念模型，所以我們對課程講義進行文本挖掘、並從中提取關鍵字，之後再利用課程講義的結構來提取關鍵字之間的關係。
每一個知識地圖都是基於講義的結構，是由講義的大綱、標題以及內容所組成的。
由我們的實驗結果證明得知，我們所提出知識地圖生成器的速度比專家手繪的知識地圖來的快速，並且知識地圖生成器所生成的知識地圖準確性是相對高的。
由我們系統所生成的知識地圖平均相似度高達近80％，而最高相似度可達95.8％。
研究結果表明，使用講義建立知識圖是可行的。
這個功能對於學習者來說很有價值，可以快速識別每週知識概念間的關係。
我們希望這個系統可以幫助學習者複習、整合與澄清課程概念之間的關係，所有想法與實作步驟會在接下來的內容詳細介紹。

Massive open online courses (MOOCs) offer valuable opportunities for freedom in learning; however, many learners face cognitive overload and conceptual and navigational disorientation.
Especially, when studying in the scenarios with complex material, there is a need for both effective learning strategies and the management of knowledge and information.
The knowledge maps are a powerful tool that is have the spatial learning strategies by visualizing the knowledge.
In this study, we used handouts to automatically build domain-specific knowledge maps for MOOCs.
We considered handouts as conceptual models created by teachers, and we performed text mining to extract keywords from MOOC handouts and used the structure of the handouts to extract relations between keywords.
Each knowledge map is based on the structure of the handouts, each consisting of an outline, title, and content.
Our experiments of a course prove the proposed the knowledge map generator is faster than manual knowledge map, moreover, it is quite accurate.
The average similarity of our system is high at almost 80\%, and the highest similarity one is 95.8\%.
The findings suggest that using handouts to build knowledge maps is feasible.
This feature is valuable for learners to quick identify the relation between the concepts in every week.
We hope that the proposed system help learners to review, consolidate, and clarify the relation between the concepts.
The overall idea and steps will be presented in this study.

Abstract i
中文摘要ii
Acknowledgement iii
Contents iv
List of Figures vii
List of Tables xi
Chapter 1 Introduction 1
Chapter 2 RelatedWork 4
2.1 MOOCs 4
2.1.1 Coursera 4
2.1.2 edX 5
2.1.3 Udacity 6
2.1.4 Khan Academy 7
2.1.5 Junyi Academy 8
2.1.6 FutureLearn 8
2.1.7 Open2Study 9
2.1.8 xuetangX 10
2.2 Knowledge map on MOOCs platform 10
2.2.1 Khan Academy 10
2.2.2 Junyi Academy 11
Chapter 3 System Architecture 12
3.1 Layer Structure Overview 12
3.2 Website MVC design 13
3.3 System Architecture 14
3.4 User interface module 15
Chapter 4 System Implementation 17
4.1 Web Server 17
4.1.1 Uploading material 17
4.2 Data Analysis Module 18
4.2.1 Keyword Extraction 18
4.2.1.1 Text Segmentation 19
4.2.1.2 Delete Stop Words 19
4.2.1.3 TF/IDF 19
4.2.2 Relation Extraction 21
4.2.2.1 Selecting Keywords 21
4.2.2.2 Parsing PDF 21
4.2.3 Knowledge Map Generation 23
4.3 User Interface Module 24
4.3.1 Environment 24
4.3.1.1 ShareCourse 24
4.3.1.2 Cytoscape.js 24
4.3.1.3 Bootstrap 24
4.3.2 Modified Knowledge Map 24
4.3.3 Knowledge Map Page 25
4.4 Recommender System 27
4.4.1 The Recommendation Page 28
Chapter 5 Experiment 30
5.1 Similarity between Knowledge Maps is calculated 30
5.1.1 Data Set 30
5.1.2 Method 31
5.2 Experiment Questionnaire 35
5.2.1 Data Set 35
5.2.2 Method 35
Chapter 6 Results and Analysis 36
6.1 Analysis of the Similarity for All Weeks of a ”Topics on Investment” and an ”Introduction to Computer Networks” 36
6.1.1 Topics on Investment 36
6.1.2 Introduction to Computer Networks 42
6.2 Analysis the Questionnaire 46
Chapter 7 Conclusion and FutureWork 54
Bibliography 56

[1] A. Ng and D. Koller, “Coursera,” Retrieved April 16, 2017, from the
World Wide Web: https://zh-tw.coursera.org/, 2012.
[2] M. I. of Technology and H. University, “edx,” Retrieved April 16,
2017, from the World Wide Web: https://www.edx.org/, 2012.
[3] M. S. Sebastian Thrun, David Stavens, “Udacity,” Retrieved April 16,
2017, from the World Wide Web: https://www.udacity.com/, 2012.
[4] S. Khan, “Khan academy,” Retrieved April 16, 2017, from the World
Wide Web: https://www.khanacademy.org/, 2006.
[5] 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.
[6] J. A. Ruip´erez-Valiente, P. J. Mu˜noz-Merino, C. D. Kloos, K.
Niemann, M. Scheffel, and M. Wolpers, “Analyzing the impact of
using optional activities in selfregulated learning,” IEEE Transactions
on Learning Technologies, vol. 9, no. 3, pp. 231–243, 2016.
[7] A. Sunar, S. White, N. Abdullah, and H. Davis, “How learners’
interactions sustain engagement: a mooc case study,” IEEE
Transactions on Learning Technologies, 2016.
[8] C. G. Brinton, M. Chiang, S. Jain, H. Lam, Z. Liu, and F. M. F. Wong,
“Learning about social learning in moocs: From statistical analysis to
generative model,” IEEE transactions on Learning Technologies, vol. 7,
no. 4, pp. 346–359, 2014.
[9] C. Alario-Hoyos, M. P´erez-Sanagust´ın, C. Delgado-Kloos, M.
Munoz-Organero et al., “Delving into participants’ profiles and use of
social tools in moocs,” IEEE Transactions on Learning Technologies,
vol. 7, no. 3, pp. 260–266, 2014.
[10] H. A. Fasihuddin, G. D. Skinner, and R. I. Athauda, “Boosting the
opportunities of open learning (moocs) through learning theories,”
GSTF Journal on Computing (JoC), vol. 3, no. 3, p. 112, 2013.
[11] C. D. Holley and D. F. Dansereau, Spatial learning strategies:
Techniques, applications, and related issues. Academic Press, 2014.
[12] P. W. Foos, “The effect of variations in text summarization
opportunities on test performance.” The Journal of experimental
education, vol. 63, no. 2, pp. 89–95, 1995.
[13] J. C. Nesbit and O. O. Adesope, “Learning with concept and
knowledge maps: A meta-analysis,” Review of educational research,
vol. 76, no. 3, pp. 413–448, 2006.
[14] H. Fasihuddin, G. Skinner, and R. Athauda, “Knowledge maps in
open learning environments: An evaluation from learnersn,” Journal
of Information Technology and Application in Education, vol. 4, pp.
18–29, 2015.
[15] C. YongYue and X. HuoSong, “Research on the auto-construction
methods of concept map,” in Intelligent Human-Machine Systems and
Cybernetics, 2009. IHMSC’09. International Conference on, vol. 2. IEEE,
2009, pp. 75–77.
[16] G. P. Jain, V. P. Gurupur, J. L. Schroeder, and E. D. Faulkenberry,
“Artificial intelligence-based student learning evaluation: a concept
map-based approach for analyzing a student’s understanding of a
topic,” IEEE Transactions on Learning Technologies, vol. 7, no. 3, pp.
267–279, 2014.
[17] J. H. Lee and A. Segev, “Knowledge maps for e-learning,”
Computers & Education, vol. 59, no. 2, pp. 353–364, 2012.
[18] I. M. Greca and M. A. Moreira, “Mental models, conceptual
models, and modelling,” International Journal of Science Education,
vol. 22, no. 1, pp. 1–11, 2000.
[19] M. I. of Technology and H. University, “Open edx,” Retrieved
April 16, 2017, from the World Wide Web: https://open.edx.org/, 2012.
[20] ——, “edx help center,” Retrieved April 16, 2017, from the World
Wide Web: https://support.edx.org/hc/en-us, 2012.
[21] F. X. ZHOU, “Junyi academy,” Retrieved April 16, 2017, from the
World Wide Web: https://www.junyiacademy.org/, 2012.
[22] T. O. University, “Futurelearn,” Retrieved April 16, 2017, from the
World Wide Web: https://www.futurelearn.com/, 2012.
[23] P.Wappett, “Open universities australia,” Retrieved April 16, 2017,
from theWorld Wide Web: https://www.open2study.com/courses,
2013.
[24] T. University, “Xuetangx,” Retrieved April 16, 2017, from the
World Wide Web:http://www.xuetangx.com/, 2013.
[25] D. Shah, “Xuetangx: A look at china’s first and biggest mooc
platform,” Retrieved April 16, 2017, from the World Wide Web:
https://www.class-central.com/report/xuetangx/, 2016.
[26] “Knowledge map,” Retrieved April 16, 2017, from the World Wide
Web: http://khanacademy.wikia.com/wiki/Knowledge Map.
[27] A. Leff and J. T. Rayfield, “Web-application development using
the model/view/controller design pattern,” in Proceedings of the 5th
IEEE International Conference on Enterprise Distributed Object
Computing, ser. EDOC ’01. Washington, DC, USA: IEEE Computer
Society, 2001, pp. 118–. [Online]. Available:
http://dl.acm.org/citation.cfm?id=645344.650161
[28] Microsoft, “Model-view-controller,” Retrieved April 16, 2017,
from the World Wide Web: https://msdn.microsoft.com/enus/library/ff649643.aspx.
[29] G. Salton and C. Buckley, “Term-weighting approaches in
automatic text retrieval,” Information processing & management, vol.
24, no. 5, pp. 513–523, 1988.
[30] J. Leskovec, A. Rajaraman, and J. D. Ullman, Mining of massive
datasets. Cambridge University Press, 2014.
[31] D. R. Hipp, “Sqlite,” Retrieved April 16, 2017, from the World Wide
Web: https://www.sqlite.org/, 2000.
[32] B. J. Flood, “Historical note: The start of a stop list at biological
abstracts,” Journal of the American Society for Information Science,
vol. 50, no. 12, pp. 1066–1066, 1999. [Online]. Available:
http://dx.doi.org/10.1002/(SICI)1097-4571(1999)50:12h1066::AIDASI5i3.0.CO;2-A
[33] “Jieba,” Retrieved April 16, 2017, from the World Wide Web:
https://github.com/fxsjy/jieba.
[34] H. P. Luhn, “A statistical approach to mechanized encoding and
searching of literary information,” IBM Journal of Research and
Development, vol. 1, no. 4, pp. 309–317, Oct 1957.
[35] Y. Shinyama, “Pdfminer,” Retrieved April 16, 2017, from the
World Wide Web: https://github.com/euske/pdfminer, 2004.
[36] N. T. University, “Sharecourse,” Retrieved April 16, 2017, from the
World Wide Web: http://www.sharecourse.net/sharecourse/, 2012.
[37] D. C. at the University of Toronto, “Cytoscape.js,” Retrieved April
16, 2017, from the World Wide Web: http://js.cytoscape.org/, 2015.
[38] J. T. Mark Otto, “Bootstrap,” Retrieved April 16, 2017, from
theWorldWideWeb: http://getbootstrap.com/.
[39] P.-W. O. Yi-Wei Huang, “Wordclouds,” Retrieved June 27, 2017,
from the World Wide Web: http://wordclouds.sharecourse.net/, 2017.
[40] N. T. University, “Topics on investment,” Retrieved June 21, 2017,
from the World Wide Web:
http://www.sharecourse.net/sharecourse/course/view/courseInfo/102
6, 2012.
[41] “Cosine similarity,” Retrieved June 21, 2017, from the World Wide
Web: https://en.wikipedia.org/wiki/Cosine similarity.
[42] Z. Yihua, Z. Chaoqun, Z. Tong, W. Longfeng, X. Mali, W. Dongbo,
and L. Xiaohui,
“The research of recognizing the reviews in webpages
based on calculating the similarity of dom-subtrees,” New Technology
of Library and Information Service, vol. 11, p. 012, 2013.
[43] “Small private online course,” Retrieved June 21, 2017, from
theWorldWideWeb: https://en.wikipedia.org/wiki/Small private online
course.
[44] Y.-W. Huang, “Experiment questionnaire,” Retrieved June 21,
2017, from the World Wide Web: https://goo.gl/PdiHov, 2017.
[45] “Cronbach’s alpha,” Retrieved June 21, 2017, from the World
Wide Web: https://en.wikipedia.org/wiki/Cronbach%27s alpha.
[46] “Cronbach’s alpha using spss statistics,” Retrieved June 21, 2017,
from the World Wide Web: https://statistics.laerd.com/spsstutorials/cronbachs-alpha-using-spss-statistics.php.
[47] “Ibm spss software,” Retrieved June 21, 2017, from the World
Wide Web: https://www.ibm.com/analytics/us/en/technology/spss/.
[48] “Spss statistics base 17.0 user’s guide,” Retrieved June 21, 2017,
from the World Wide Web:
https://www.jou.ufl.edu/assets/researchlab/SPSS-Statistcs-Base-UsersGuide-17.0.pdf.