RIFQY, MUHAMMAD NIZAR (2024) ANALISIS SENTIMEN ULASAN PADA PERUSAHAAN PENYEDIA JASA LAYANAN LOGISTIK JNE MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE DAN K-NEAREST NEIGHBORS (KNN). S1 thesis, Universitas Mercu Buana-Menteng.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (Cover)
41520010132-MUHAMMAD NIZAR RIFQY-01 Cover - Muhammad Nizar Rifqy.pdf Download (304kB) |
|
Text (Abstrak)
41520010132-MUHAMMAD NIZAR RIFQY-02 Abstrak - Muhammad Nizar Rifqy.pdf Download (162kB) |
|
Text (Bab 1)
41520010132-MUHAMMAD NIZAR RIFQY-03 Bab 1 - Muhammad Nizar Rifqy.pdf Restricted to Registered users only Download (76kB) |
|
Text (Bab 2)
41520010132-MUHAMMAD NIZAR RIFQY-04 Bab 2 - Muhammad Nizar Rifqy.pdf Restricted to Registered users only Download (338kB) |
|
Text (Bab 3)
41520010132-MUHAMMAD NIZAR RIFQY-05 Bab 3 - Muhammad Nizar Rifqy.pdf Restricted to Registered users only Download (95kB) |
|
Text (Bab 4)
41520010132-MUHAMMAD NIZAR RIFQY-06 Bab 4 - Muhammad Nizar Rifqy.pdf Restricted to Registered users only Download (585kB) |
|
Text (Bab 5)
41520010132-MUHAMMAD NIZAR RIFQY-07 Bab 5 - Muhammad Nizar Rifqy.pdf Restricted to Registered users only Download (71kB) |
|
Text (Daftar Pustaka)
41520010132-MUHAMMAD NIZAR RIFQY-08 Daftar Pustaka - Muhammad Nizar Rifqy.pdf Restricted to Registered users only Download (173kB) |
|
Text (Lampiran)
41520010132-MUHAMMAD NIZAR RIFQY-09 Lampiran - Muhammad Nizar Rifqy.pdf Restricted to Registered users only Download (326kB) |
|
Text (Lembar Keabsahan)
41520010132-MUHAMMAD NIZAR RIFQY-10 Hasil Scan Formulir Pernyataan Keabsahan dan Persetujuan Publikasi Tugas Akhir - Muhammad Nizar Rifqy.pdf Restricted to Repository staff only Download (136kB) |
Abstract
Penelitian ini bertujuan menganalisis sentimen ulasan terhadap layanan logistik JNE menggunakan algoritma Support Vector Machine (SVM) dan K-Nearest Neighbors (KNN). Data diperoleh dari Twitter melalui teknik crawling dan diproses dengan tahap preprocessing. Tujuan utama adalah membandingkan kinerja SVM dan KNN dalam mengklasifikasikan sentimen pelanggan. Hasil menunjukkan bahwa KNN mengungguli SVM di semua skenario pengujian (60-40, 70-30, dan 80- 20). KNN mencapai Accuracy 95,18%, 96,20%, dan 97,37%, sementara SVM mencapai 94,52%, 94,15%, dan 96,05%. Precision, Recall, dan F1-score dari KNN juga lebih tinggi atau setara dengan SVM dalam beberapa skenario. Berdasarkan hasil ini, KNN terbukti lebih efektif untuk analisis sentimen ulasan layanan JNE di Twitter. This study aims to analyze sentiment in reviews of JNE logistics services using Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) algorithms. Data was obtained from Twitter through crawling techniques and processed with preprocessing steps. The main objective is to compare the performance of SVM and KNN in classifying customer sentiment. The results show that KNN outperforms SVM in all testing scenarios (60-40, 70-30, and 80-20). KNN achieved accuracies of 95.18%, 96.20%, and 97.37%, while SVM achieved 94.52%, 94.15%, and 96.05%. The precision, recall, and F1-score of KNN were also higher or equal to those of SVM in several scenarios. Based on these results, KNN is proven to be more effective for sentiment analysis of JNE service reviews on Twitter.
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41520010132 |
| Uncontrolled Keywords: | Analisis sentimen, Twitter, JNE, Support Vector Machine (SVM), K-Nearest Neighbors (KNN). Sentiment Analysis, Twitter, JNE, Support Vector Machine (SVM), K-Nearest Neighbors (KNN). |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika |
| Divisions: | Fakultas Ilmu Komputer > Informatika |
| Depositing User: | NAYLA AURA RAYANI |
| Date Deposited: | 29 Jun 2024 02:51 |
| Last Modified: | 29 Jun 2024 02:51 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/89278 |
Actions (login required)
 |
View Item |
