Skripsi

STUDI KOMPARATIF ALGORITMA KLASIFIKASI DALAM MENGANALISIS SENTIMEN APLIKASI SIGNAL DENGAN PENDEKATAN SMOTE

---

Public service applications such as SIGNAL facilitate the public in accessing information and making motor vehicle tax payments. However, the diversity of user reviews indicates the need to evaluate public perceptions through sentiment analysis. This study compares the performance of four classification algorithms Naïve Bayes, Random Forest, Decision Tree, and SVM in analyzing 36,000 user reviews of the SIGNAL application obtained from the Google Play Store. The data underwent preprocessing, feature extraction using TF-IDF, and class balancing with the SMOTE technique, followed by evaluation using accuracy, precision, recall, and F1-score metrics. The results show that the Random Forest algorithm achieved the best performance with an accuracy of 91.04% and an F1-score of 94.80%, followed by Naïve Bayes, SVM, and Decision Tree. These findings indicate that Random Forest is the most effective for balanced datasets, while SVM and Naïve Bayes demonstrate competitive precision. The outcomes of this research can be utilized by developers and related institutions to optimize digital public services, making them more responsive to user needs

---

Availability

Detail Information

Series Title

-

Call Number

T1895352025

Publisher

Indralaya : Prodi Sistem Informasi, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xv, 70 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

006.350 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Informasi
Pembelajaran Mesin--Analsis Sintemen

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment