Implementasi Text Mining Pada Sistem Informasi Pengaduan Mahasiswa Dengan Support Vector Machine

Luandy, Nico Libriawan (2020) Implementasi Text Mining Pada Sistem Informasi Pengaduan Mahasiswa Dengan Support Vector Machine. Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstract) 7. ABSTRACT.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (87kB)
	Text (Bab 1 Pendahuluan) 14. BAB 1. PENDAHULUAN.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (122kB)
	Text (Daftar Pustaka) 19. DAFTAR PUSTAKA.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (98kB)
	Text (Laporan Lengkap) 21. E41150728 - LAPORAN LENGKAP SKRIPSI.pdf Restricted to Registered users only Download (2MB)

Abstract

A college in forming students who have high competitiveness requires a variety of infrastructure facilities and good synergy between academicians, especially in the Majoring of Information Technology, State Polytechnic of Jember. Besides that, the student’s role in expressing their aspirations while on campus life is very important. But not all students dare to express positive aspirations, known as student complaints. Forms of complaints generally still use a manual system that is through oral or written in the questionnaire document and tends not to be processed or taken seriously and not classified according to the problem. Based on these problems can be resolved by implementing text mining and algorithm support vector machine (svm) in classifying student complaints in the form of text. Complaints category in the form of infrastructure and academicians. The results showed the most optimal level of accuracy using k-fold cross validation with K = 6 and γ = 0.01 produced an average accuracy of 73.1% and the results of testing with confusion matrix produced the most optimal accuracy rate of 97.4%. The information system in this research is based on Android and integrated into the web so that the admin can process the data into reports.

Actions (login required)

View Item