Developing a warning system in online learning

HO CHI MINH CITY UNIVERSITY OF TECHNOLOGY COMPUTER SCIENCE AND ENGINEERING DEPARTMENT THESIS PROPOSAL Developing A Warning System In Online Learning COUNCIL: INFORMATION SYSTEMS SUPERVISOR: Dr VO THI NGOC CHAU REVIEWER: Assoc Prof NGUYEN THANH BINH —o0o— STU 1: NGUYEN QUANG MANH - 1652366 HO CHI MINH CITY, 2022 INSURANCE Our team hereby guarantees that this graduation thesis is performed by our own team and not copied All the materials we have used in our thesis all have their name, source and presented in ”REFERENCES” ACKNOWLEDGEMENTS First, we would like to express our gratitude to Dr Vo Thi Ngoc Chau Thanks to his knowledge and experience that we were able to overcome the difficulties of this thesis He was the one to guide through the thesis and show us our mistakes during the planning and implementation as well as provide solutions to our problem Next, we would like to send our gratitude to the teachers, professors and staffs in Ho Chi Minh City University of Technology, especially the ones in Computer Science and Computer Engineering department for teaching new knowledge to us and supporting us through our time in the university Thanks to the knowledge which you have taught us that we were able to finish this thesis We also would like to thank our parents, our friends who not only supported us physically through the time of this thesis but also mentally Thank you for being there when we needed Finally, we wish everyone the best The time we have had here at Ho Chi Minh City University of Technology will always remain one of the most beautiful memories in our heart Once again, we would like to thanks everyone for your support Contents Introduction 1.1 Project introduction 1.2 Why I choose this topic 1.3 Objectives and content 1.3.1 Objectives 1.3.2 Content 1.4 Boundary of the project 1.5 Structure of the thesis 1 1 2 2 Related Works 2.1 Survey similar systems 2.1.1 Early warning systems to predict students online learning performance 2.1.2 Developing an early-warning system for spotting at-risk students by using eBook interaction logs 2.2 Survey system development 2.2.1 Front-end framework 2.2.2 Back-end framework 2.3 Survey other related technologies 2.3.1 Introduction Project analysis 3.1 Requirements 3.1.1 Educators 3.1.2 Students 3.1.3 Parents 3.2 Use-case Diagram 3.2.1 Educators 3.2.2 Students 3.2.3 Parents 3.3 Activity Diagram 3.3.1 Activity Diagram For User Login 3.3.2 Activity Diagram for Educator to compare between student’s indicators 3.3.3 Activity Diagram for Educator to confirm students who are at risk 3.4 System Architecture 3.5 Database Design 3.5.1 Requirements 3.5.2 Specify Entity Types 3.5.3 Specify Relationship Types 3.5.4 Entity Relationship Diagram ii 7 8 10 11 11 11 12 13 14 15 15 16 16 17 3.6 Data Mining Techniques 17 3.6.1 Logistic Regression 18 3.6.2 Random Forest 18 System design 4.1 Application architecture 4.2 Database design 4.3 Prepare Data 4.4 Data Mining 4.4.1 Collect data for applying data mining 4.4.2 Define Problem 4.4.3 Evaluate data mining algorithms using scikit-learn library 20 21 23 32 35 35 35 35 37 37 37 37 48 Conclusion 6.1 Accomplished Result 6.2 Limitation 6.3 Future work 50 50 50 50 References 51 Appendices 53 A Test case table for early warning system 54 Application implementation (Demo version) 5.1 Website 5.1.1 Back-end 5.1.2 User Interface 5.1.3 Improve Website Performance List of Tables 4.1 4.2 Data Mining Evaluation 35 Confusion Matrix from Random Forest 35 A.1 Test cases table for the website 54 iv List of Figures 3.1 3.2 3.3 3.4 3.5 3.6 3.7 3.8 3.9 3.10 3.11 3.12 Educator Use-case Diagram Student Use-case Diagram Parents Use-case Diagram Activity Diagram for Login Activity Diagram for Educator to compare between student’s indicators Activity Diagram for Educator to confirm students who are at risk System Architecture Entity Relationship Diagram Logistic Regression Implementation Using Scikit-learn Logistic Regression Result Random Forest Implementation Using Scikit-learn Random Forest Result 10 11 12 13 14 15 17 18 18 19 19 4.1 4.2 4.3 4.4 4.5 4.6 4.7 4.8 4.9 4.10 4.11 4.12 4.13 4.14 4.15 4.16 4.17 Website architecture Student Information Student Register Student Interaction Student Assessments Assessments Student Assessments Materials Course Information Warning User Account Messages Educator Parents Create Data Sample Add Visit Number for Interaction of Each Student Arrange courses for educators 22 23 24 24 25 26 26 27 28 29 29 30 31 32 33 33 34 5.1 5.2 5.3 5.4 5.5 5.6 5.7 5.8 5.9 5.10 Login Page Course List of Educator Course Details of Educator Materials and Assessments in Courses Student Detail of Educator Educator Dashboard Course List of Student Course Details of Student Student Assessments Student Profile 38 39 40 40 41 41 42 42 43 43 v of Educator Figure 5.3: Course Details of Educator • They also see the material list and the assessment list of each course Figure 5.4: Materials and Assessments in Courses of Educator • When educators click on a student in student list They can view the student detail • Educators can view the student information in detail • If the student was predicted as a at-risk student, the educator would able to warn the student • If the student was warned already, the button would be disabled • Educators can view assessment results of students 40 Figure 5.5: Student Detail of Educator • Educators can view the dashboard which shows overall statistics about courses and students they manage Figure 5.6: Educator Dashboard 41 c Student • After students login successfully, they are able to view all courses that they registered Figure 5.7: Course List of Student • Students can click on a course to view in detail After choosing a course, they can view the course information details such as name, code, number of students, etc • Students can contact with their educators of the course Figure 5.8: Course Details of Student • They also see the material list and the assessment list of each course • In assessment list, students can view results of their all assessments 42 Figure 5.9: Student Assessments • Students can view their individual information Figure 5.10: Student Profile • Students can view their warnings (if any) 43 Figure 5.11: Student Warning • Students can view the dashboard which shows relevant statistics 44 d Parents • After Parents login successfully, they are able to view all courses that their children registered Figure 5.12: Course List of Child • Parents can click on a course to view in detail After choosing a course, they can view the course information details such as name, code, number of students, etc • Parents can contact with educators in the course • They also see the the assessment list of their children in each course • Parents can view their individual information • Parents can view warnings about their children (if any) 45 Figure 5.13: Parents Warning • Parents can view the dashboard which shows statistics related to their children 46 e Pages for all users • Educators can interact with students as well as parents and vice versa Figure 5.14: Message • In the setting page, users can change the password of their accounts • Users are able to change the theme of the website Figure 5.15: Settings 47 5.1.3 Improve Website Performance I use Lighthouse extension to check the performance of my website and then refactor my source code • Before improvement: Figure 5.16: Before Improvement 48 • After Improvement: Figure 5.17: After Improvement 49 Chapter Conclusion 6.1 Accomplished Result • Complete Research current educational warning systems • Complete Design system architecture • Complete Research and learn front-end framework to build front-end website • Complete Research and learn back-end framework and Database Server to build back-end website • Complete Research technologies related to our project • Complete Research some related data mining algorithms • Complete Build Website for an early warning system • Complete Integrate Gmail API to the website • Complete Integrate suitable data mining techniques to the website 6.2 Limitation • The data is collected from the internet and edited, it is not official data of an university • The website have not been connected with a real online learning platform 6.3 Future work • Improve UI and UX of the website • Improve data mining algorithms used in the application • Collect more data and data-sets in order to improve model accuracy 50 Bibliography [1] Ya-HanHu, Chia-LunLoa, Sheng-PaoShihb (2014) Early warning systems to predict students online learning performance Computers in Human Behavior Volume 36, July 2014, Pages 469-478 Retrieved from https://www.sciencedirect.com/science/article/abs/pii/S0747563214002118 at 15/12/2022 [2] Găokhan Akácapnar (2019) Developing an early-warning system for spotting at-risk students by using eBook interaction logs Smart Learning Environments volume 6, Article number: (2019) Retrieved from https://slejournal.springeropen.com/articles/10.1186/s40561-019-0083-4 at 15/12/2022 [3] https://reactjs.org/ Reactjs Retrieved from https://reactjs.org/ at 15/12/2022 [4] https://vuejs.org Vuejs Retrieved from https://vuejs.org at 15/12/2022 [5] https://angular.io/ Angular Retrieved from https://angular.io/ at 15/12/2022 [6] https://www.djangoproject.com/ Django https://www.djangoproject.com/ at 15/12/2022 Retrieved from [7] Flask’s documentation Flask Retrieved from https://flask.palletsprojects.com/en/2.0.x at 15/12/2022 [8] https://scikit-learn.org/stable/ Scikit-learn learn.org/stable/ at 15/12/2022 Retrieved from [9] https://imbalanced-learn.org/stable/ Imbalanced-learn https://imbalanced-learn.org/stable/ at 15/12/2022 https://scikit- Retrieved from [10] Oracle CloudWorld (Octorber 2022) MySQL Retrieved from http://www.mysql.com/ at 15/12/2022 [11] Sommerville, Ian (2016) Software engineering-Addison-Wesley 51 [12] (ITPro collection Morgan Kaufmann series in data management systems) Jiawei Han, Micheline Kamber, Jian Pei (2012) Data Mining Concepts and TechniquesMorgan Kaufmann Publishers [13] Ramez Elmasri, Shamkant B Navathe (2016) Fundamentals of Database Systems (7th edition) published by Pearson [14] Christothea Herodotou, Bart Rienties, Avinash Boroowa, Zdenek Zdr´ahal (July 2019) A large-scale implementation of predictive learning analytics in higher education: the teachers’ role and perspective Educational Technology Research and Development 67(2) [15] Jakub Kuzilek (2015) Open University Learning Analytics dataset Data Set Retrieved from https://archive.ics.uci.edu/ml/datasets/Open+University Learning Analytics+dataset at 15/12/2022 52 Appendices 53 Appendix A Test case table for early warning system Id Test case description Login as educator Expected result Actual result Status Tester Able to be in educator dashboard Able to be in educator dashboard Pass Login as student Able to be in student dashboard Able to be in student dashboard Pass Login as parents Able to be in parent dashboard Able to be in parent dashboard Pass Login with wrong password or account Student navigate to course list page Student click to a course in list Educator navigate to course list page Educator click to a course in list Educator click to a student in student list Able to show a notification that ”invalid account” Able to show a notification that ”invalid account” Pass Able to see all courses Able to see all courses Pass Able to see detail of the courses Able to see detail of the courses Pass Able to see all courses Able to see all courses Pass Able to see the course detail and all students in the course Able to see the student progress and warn student if he/she is at risk Able to see the course detail and all students in the course Able to see the student progress and warn student if he/she is at risk Pass 8 Table A.1: Test cases table for the website 54 Pass Nguyen Quang Manh Nguyen Quang Manh Nguyen Quang Manh Nguyen Quang Manh Nguyen Quang Manh Nguyen Quang Manh Nguyen Quang Manh Nguyen Quang Manh Nguyen Quang Manh