Natasya Febriyanti, . (2024) SENTIMEN ANALISIS KOMENTAR VIDEO YOUTUBE MENGENAI PENERAPAN JALAN BERBAYAR ELEKTRONIK (ELECTRONIC ROAD PRICING) DI DKI JAKARTA DENGAN METODE SUPPORT VECTOR MACHINE DAN ASOSIASI KATA. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (23kB) |
|
Text
AWAL.pdf Download (654kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (291kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (546kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (445kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (78kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (182kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (89kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (743kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (379kB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (669kB) |
Abstract
The DKI Jakarta Transportation Agency is planning to implement an Electronic Road Pricing (ERP) system on 25 protocol roads in Jakarta. There have been public responses to this policy plan, which have been conveyed through youtube videos on the CNBC Indonesia channel. If these comments are combined and processed using a sentiment analysis approach, they can be classified as having a positive, negative or neutral sentiment. This study aims to classify 1196 public comments on the policy plan for 25 Paid Roads in DKI Jakarta into positive, negative, and neutral sentiment using the Support Vector Machine (SVM) method. SVM is a classification method that cannot map non-linear data to obtain an optimal hyperplane. To achieve the best classification accuracy, an additional kernel trick called Radial Basis Function (RBF) is applied. This utilises Grid Search to determine the optimal combination of Cost and Gamma parameters. Additionally, there is an imbalance between major and minor classes that needs to be addressed. Therefore, the SMOTE method is used to overcome this imbalance. Using a combination of several methods, an accuracy value of 90.6% was achieved. This indicates that the combination of methods is effective in classification.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010512025] [Pembimbing 1: Nur Hafifah Matondang] [Pembimbing 2: Bambang Tri Wahyono] [Penguji 1: Iin Ernawati] [Penguji 2: Ika Nurlaili] |
| Uncontrolled Keywords: | ERP, Sentiment Analysis, Paid Road, Congestion, Support Vector Machine |
| Subjects: | Q Science > QA Mathematics 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: | NATASYA FEBRIYANTI |
| Date Deposited: | 10 Sep 2024 07:50 |
| Last Modified: | 10 Sep 2024 07:50 |
| URI: | http://repository.upnvj.ac.id/id/eprint/31613 |
Actions (login required)
 |
View Item |