Skripsi

ANALISIS SENTIMEN TERHADAP ULASAN APLIKASI MOBILE JKN BERBASIS INDOBERT

---

Mobile JKN is a digital innovation by BPJS Kesehatan designed to simplify access to National Health Insurance (JKN) services. However, user reviews on the Google Play Store indicate technical barriers affecting participant satisfaction. This study aims to analyze user sentiment using the IndoBERT model, a transformer-based architecture pre-trained on billions of Indonesian words to accurately recognize both formal and informal sentence structures.The research methodology includes data preprocessing using deduplication techniques, resulting in 7,063 unique data points. To address the limited variation, data augmentation was performed by adding 6,106 new data points specifically for the training path. The model was trained using the data splitting method and optimized using the Optuna framework to find the best parameters.The results show that the optimal configuration in Trial ID 3 achieved an overall accuracy of 91.00% on 707 test data points. The model demonstrated stable performance with an F1-score of 0.91 for the negative class and 0.92 for the positive class. The implementation of IndoBERT combined with data augmentation and Optuna optimization proved effective in mapping public perception. These analysis results are expected to serve as a guide for BPJS Kesehatan in refining digital services to better meet user needs. Keywords: Sentiment Analysis, IndoBERT, Mobile JKNAugmentation,Optuna

---

Availability

Detail Information

Series Title

-

Call Number

T1930602026

Publisher

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

Collation

xvii, 146 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

005.107

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Aplikasi Mobile JKN
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment