Perancangan dan pengembangan educational data mining (edm) dalam pengolahan data survei umpan balik menggunakan teknik classification dan clustering pada Universitas XYZ = Design and development of educational data mining (edm) for processing the survei feedback data using classification and clustering techniques at University XYZ

Daicy, Wivina (2021) Perancangan dan pengembangan educational data mining (edm) dalam pengolahan data survei umpan balik menggunakan teknik classification dan clustering pada Universitas XYZ = Design and development of educational data mining (edm) for processing the survei feedback data using classification and clustering techniques at University XYZ. Bachelor thesis, Universitas Pelita Harapan.

	Text (Title) Title.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
Preview	Text (Abstract) Abstract.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (305kB) | Preview
Preview	Text (ToC) ToC.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) | Preview
Preview	Text (Chapter1) Chapter1.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (374kB) | Preview
	Text (Chapter2) Chapter2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (3MB)
	Text (Chapter3) Chapter3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB)
	Text (Chapter4) Chapter4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (31MB)
	Text (Chapter5) Chapter5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (189kB)
Preview	Text (Bibliography) Bibliography.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (653kB) | Preview
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (4MB)

Abstract

Universitas XYZ merupakan salah satu perguruan tinggi swasta yang memiliki kewajiban untuk memperhatikan evaluasi dari peserta didik melalui data survei umpan balik. Pengolahan survei umpan balik secara konvensional tidak cukup untuk mengeksplorasi pengetahuan secara mendalam. Oleh karena itu, penelitian ini bertujuan untuk mengembangkan Educational Data Mining (EDM) dalam pengolahan survei umpan balik supaya dapat mengeksplorasi data survei umpan balik secara lebih mendalam. Penelitian ini memanfaatkan EDM untuk mengolah dan mengeksplorasi data survei umpan balik dari Universitas XYZ bagian Open Ended Question (OEQ) dan Close Ended Question (CEQ) pada survei Student Feedback Questionnaire (SFQ), Facility Satisfaction Questionnaire (FSQ), dan Graduate Feedback Questionnaire (GFQ). Penelitian ini melakukan teknik classification untuk memprediksi label aspek komentar survei berbentuk OEQ. Penelitian ini menghasilkan model multi class classification terbaik pada SFQ menggunakan algoritma SVM dengan ratarata nilai evaluasi sebesar 69.82%. Pada FSQ, diperoleh model multi label classification terbaik menggunakan algoritma SVM dan Classifier Chain sebagai library multi label terbaik dengan rata-rata nilai evaluasi sebesar 73.325%. Pada GFQ, diperoleh model multi label classification terbaik menggunakan algoritma MLP dengan rata-rata nilai evaluasi sebesar 60.675%. Penelitian ini juga melakukan teknik clustering untuk mengelompokkan responden survei CEQ. Pada SFQ, diperoleh model clustering terbaik dengan menggunakan algoritma K-Means dengan rata-rata nilai evaluasi sebesar 0.582. Pada FSQ dan GFQ, diperoleh model clustering terbaik dengan menggunakan algoritma Fuzzy C Means dengan rata-rata nilai evaluasi sebesar 0.586 untuk survei FSQ dan 0.599 untuk survei GFQ. / XYZ University is one of the private universities that has an obligation to pay attention to the evaluation from stakeholders including the students through feedback survey data. The conventional feedback survey processing is not enough to explore deeper knowledge from the survey. Because of that, the purpose of the research is to develop an Educational Data mining (EDM) for feedback survey processing to explore the feedback survey thoroughly. This research uses EDM to process and explore the feedback survey data that contains of Open-Ended Question (OEQ) and Close-Ended Question (CEQ) for Student Feedback Questionnaire (SFQ), Facility Satisfaction Questionnaire (FSQ), and Graduate Feedback Questionnaire (GFQ). This research uses classification techniques to predict the aspect label of the survey in the open-ended questionnaire. This research concludes the best multi class classification model for SFQ using the SVM algorithm with the evaluation score average is 69.82%. For the FSQ, the best multi label classification model is derived using the SVM algorithm and the classifier chain as the best library multi label with the evaluation score average is 73.325%. For the GFQ, the best multi label classification model is derived using the MLP algorithm with the evaluation score average is 60.675%. This research is also using clustering techniques for grouping the CEQ survey respondent. For SFQ, the best clustering model is derived from the K-Means algorithm with the evaluation score average is 0.582. For the FSQ and the GFQ, the best clustering model is derived from the Fuzzy C Means algorithm with evaluation score average is 0.586 for the FSQ survey and 0.599 for the GFQ survey.

Actions (login required)

View Item