PERBANDINGAN METODE NAIVE BAYES, K-NEAREST NEIGHBOR, DAN SUPPORT VECTOR MACHINE PADA SISTEM PENGADUAN PELAYANAN (STUDI KASUS: FAKULTAS ILMU KOMPUTER UNIVERSITAS PEMBANGUNAN NASIONAL “VETERAN” JAKARTA)

Fadiyah Sutopo, . (2024) PERBANDINGAN METODE NAIVE BAYES, K-NEAREST NEIGHBOR, DAN SUPPORT VECTOR MACHINE PADA SISTEM PENGADUAN PELAYANAN (STUDI KASUS: FAKULTAS ILMU KOMPUTER UNIVERSITAS PEMBANGUNAN NASIONAL “VETERAN” JAKARTA). Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (119kB)
[img] Text
AWAL.pdf
Download (626kB)
[img] Text
BAB I.pdf
Download (149kB)
[img] Text
BAB II.pdf
Restricted to Repository UPNVJ Only
Download (351kB)
[img] Text
BAB III.pdf
Restricted to Repository UPNVJ Only
Download (177kB)
[img] Text
BAB IV.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
BAB V.pdf
Download (131kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (209kB)
[img] Text
DAFTAR RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (122kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (1MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (540kB)

Abstract

Good service is one of the main components for a company or institution and can enhance user satisfaction, as well as build a positive reputation. The provision of service complaint facilities is used to accommodate reports that will subsequently be followed up in an effort to improve services. Currently, the Faculty of Computer Science at Universitas Pembangunan Nasional "Veteran" Jakarta provides a Google Form-based service complaint form to handle complaint. Therefore, the author developed a web-based service complaint system for the Faculty of Computer Science at Universitas Pembangunan Nasional "Veteran" Jakarta, comparing three algorithms: Naïve Bayes, K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). These algorithms were compared to automatically classify complaint data according to the relevant service department. Based on testing with 234 data samples, SVM achieved the highest accuracy at 95%, followed by Naïve Bayes at 89%, and KNN at 80%. SVM was then implemented into the system using HTML, CSS, JavaScript, Flask, and MySQL, and blackbox testing was conducted to ensure that the system's output meets expectations, especially for automatically classifying complaints according to their service department. It is hoped that this will enhance the quality of complaint services at the Faculty of Computer Science, Universitas Pembangunan Nasional "Veteran" Jakarta.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2010512110] [Pembimbing 1: Bambang Saras Yulistiawan] [Pembimbing 2: Rudhy Ho Purabaya] [Penguji 1: Tjahjanto] [Penguji 2: Zatin Niqotaini]
Uncontrolled Keywords: Service Complaints, Comparison, Naive Bayes, K-Nearest Neighbor, Support Vector Machine
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Q Science > QA Mathematics > QA76 Computer software
Divisions: Fakultas Ilmu Komputer > Program Studi Sistem Informasi (S1)
Depositing User: FADIYAH SUTOPO
Date Deposited: 01 Aug 2024 20:41
Last Modified: 30 Aug 2024 08:48
URI: http://repository.upnvj.ac.id/id/eprint/31774

Actions (login required)

View Item View Item