Skripsi

ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI DANA DI GOOGLE PLAY STORE MENGGUNAKAN HYBRID METHOD RANDOM FOREST DAN SUPPORT VECTOR MACHINE(SVM)

---

This research aims to develop an automated sentiment analysis model using a hybrid method of Random Forest (RF) and Support Vector Machine (SVM) to evaluate DANA application user reviews on the Google Play Store. A total of 50,001 secondary review data from Kaggle were used in this study, partitioned into 80% training data and 20% testing data. The analysis process includes text preprocessing and Term Frequency-Inverse Document Frequency (TF-IDF) weighting. The classification process is then carried out using a Soft Voting mechanism that combines the prediction probabilities of the RF and SVM models. The evaluation results show that the hybrid model achieved the highest accuracy of 84.0%, outperforming the individual SVM (83.9%) and RF (82.1%) algorithms. In conclusion, the hybrid method is proven to be more effective and stable in classifying unstructured Indonesian review sentiments, even on the original data distribution.

---

Availability

Detail Information

Series Title

-

Call Number

T2008192026

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xvii, 106 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

006.312 07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
Analisis Penggunaan Aplikasi Dana

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment