Skripsi

ANALISIS SENTIMEN ULASAN PENGGUNA GOPAY MENGGUNAKAN INDOBERT

---

The rapid growth of digital wallets in Indonesia, particularly GoPay, has generated tens of thousands of user reviews containing valuable information about service satisfaction. This study aims to classify GoPay application user satisfaction into positive, neutral, and negative categories using the Fine-Tuning IndoBERT (Indonesian BERT) method. As a Transformer-based model trained specifically on Indonesian language corpora, IndoBERT has advantages in understanding informal language and slang commonly used in user reviews. To maximize model performance and address the challenges of manual parameter selection, this study applies automatic hyperparameter optimization using Grid Search. Based on experimental results, the best parameter configuration was obtained using a learning rate of 5 x 10-5, batch size 16, and a training duration of 4 epochs. The final evaluation against the test data under the best scenario (Mixed Balancing) demonstrates a highly robust performance, achieving an accuracy of 95% and a weighted average F1-Score of 0.95. Keywords: Sentiment Analysis, GoPay, IndoBERT, Fine-tuning, Grid Search, Transformers, Text Classification.

---

Availability

Detail Information

Series Title

-

Call Number

T1959122026

Publisher

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

Collation

xv, 121 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.307

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
GoPay

Specific Detail Info

-

Statement of Responsibility

TUTI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment