Sholihah, Eka Rizqi Mar'atus (2024) ANALISIS SENTIMEN ULASAN PENGGUNA KAI ACCESS PADA GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM). Undergraduate thesis, Universitas Pembangunan Nasional "Veteran" Jawa Timur.
|
Text (Cover)
19081010022_Cover.pdf Download (473kB) | Preview |
|
|
Text (Bab 1)
19081010022_BAB 1.pdf Download (81kB) | Preview |
|
![[img]](http://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Bab 2)
19081010022_BAB 2.pdf Restricted to Registered users only until 19 January 2027. Download (147kB) |
|
|
Text (Bab 3)
19081010022_BAB 3.pdf Restricted to Registered users only until 19 January 2027. Download (320kB) |
|
|
Text (Bab 4)
19081010022_BAB 4.pdf Restricted to Registered users only until 19 January 2027. Download (1MB) |
|
|
Text
19081010022_BAB 5.pdf Download (70kB) | Preview |
|
|
Text
19081010022_Daftar Pustaka.pdf Download (19kB) | Preview |
Abstract
KAI Access is an online mobile ticketing application owned by PT Kereta Api Indonesia (Persero). This application can be downloaded through app distribution platforms such as the Google Play Store. On the Google Play Store, application users can provide reviews and ratings related to the KAI Access application. These reviews and ratings will serve as considerations for other customers who are about to download the application, as they will shape the users' perception of the application. To understand the reviews or detect the sentiment expressed by users toward the application, it is important to perform sentiment analysis techniques. In this research, sentiment analysis will be implemented using the support vector machine (SVM) algorithm on the reviews of the KAI Access application on the Google Play Store. The goal of this study is to measure the performance level of the SVM algorithm with linear and radial basis function (RBF) kernels in classifying sentiment into two classes: positive sentiment and negative sentiment. This research utilizes 10,000 data points from the reviews of the KAI Access application on the Google Play Store. From several conducted tests, the SVM with linear kernel was able to produce a sentiment analysis model with the highest accuracy, which is 83.1%. Meanwhile, for SVM with RBF kernel, through various tests conducted, it was able to generate a sentiment analysis model with the highest accuracy, which is 86.1%.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | T Technology > T Technology (General) | ||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | Eka Rizqi Mar'atus Sholihah | ||||||||||||
| Date Deposited: | 19 Jan 2024 06:36 | ||||||||||||
| Last Modified: | 19 Jan 2024 06:36 | ||||||||||||
| URI: | http://repository.upnjatim.ac.id/id/eprint/20198 |
Actions (login required)
 |
View Item |