Analisis Sentimen Berbasis Aspek Pada Ulasan Multibahasa Dari Aplikasi Gobis Suroboyo Menggunakan Lda dan Svm

Puspitasari, Dianita (2025) Analisis Sentimen Berbasis Aspek Pada Ulasan Multibahasa Dari Aplikasi Gobis Suroboyo Menggunakan Lda dan Svm. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 21082010070.-cover.pdf Download (1MB)
	Text (Bab 1) 21082010070.-bab1.pdf Download (369kB)
	Text (Bab 2) 21082010070.-bab2.pdf Restricted to Repository staff only until 13 June 2027. Download (393kB)
	Text (Bab 3) 21082010070.-bab3.pdf Restricted to Repository staff only until 13 June 2027. Download (329kB)
	Text (Bab 4) 21082010070.-bab4.pdf Restricted to Repository staff only until 13 June 2027. Download (1MB)
	Text (Bab 5) 21082010070.-bab5.pdf Download (216kB)
	Text (Daftar Pustaka) 21082010070.-daftarpustaka.pdf Download (197kB)
	Text (Lampiran) 21082010070.-lampiran.pdf Restricted to Repository staff only until 13 June 2027. Download (236kB)

Abstract

The GOBIS (Golek Bis) application is a digital service from the Surabaya City Transportation Agency that provides public transportation information. This application was created to reduce congestion. Although it has been downloaded more than 100 thousand times, there are still many user complaints recorded on the application review page. These reviews are written in various languages, which is a challenge in the data management and analysis process. Therefore, this study is limited to only Indonesian and English reviews to ensure consistency of analysis. This study uses the Aspect-Based Sentiment Analysis (ABSA) approach to analyze reviews with the Latent Dirichlet Allocation (LDA) method for aspect identification and the Support Vector Machine (SVM) algorithm for sentiment classification. The purpose of this study is to identify the dominant aspects in user reviews of the GOBIS Suroboyo application and evaluate the performance of the SVM algorithm based on evaluation metrics such as accuracy, precision, recall, and F1-score. The results of the study show six main aspects that often appear in reviews, namely Application Features and Development, User Suggestions and Service Innovation, Error and Location Accuracy, Delay and Application Usability, Comfort and Service Quality, and Route Tracking and Vehicle Information. The SVM model based on the results from the 10-fold cross-validation scenario on normal data shows fairly good performance in sentiment classification with an accuracy of 0.7416, precision of 0.7376, recall of 0.7354, and F1-score of 0.7363.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Wahyuni, Eka Dyar	NIDN0001128406	ekawahyuni.si@upnjatim.ac.id
Thesis advisor	Permatasari, Reisa	NIDN0014059203	reisa.permatasari.sifo@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Information Systems

Depositing User:

Dianita Puspita sari

Date Deposited:

13 Jun 2025 08:47

Last Modified:

13 Jun 2025 08:47

URI:

https://repository.upnjatim.ac.id/id/eprint/37620