Skripsi

SENTIMEN ANALISIS ULASAN PENGGUNA APLIKASI WONDR BY BNI DENGAN METODE NAIVE BAYES

---

Penilaian

---

The advancement of digital technology has driven the emergence of various financial service applications, including Wondr by BNI, the latest mobile banking app from Bank Negara Indonesia. This study aims to analyze user sentiment toward the application using the Naïve Bayes classification method. A total of 4,970 user reviews from Google Play Store were analyzed following the CRISP-DM framework, with preprocessing steps including cleansing, tokenizing, stopword removal, and TF-IDF weighting. Modeling was conducted using RapidMiner and Google Colaboratory. The model achieved an accuracy of 71,63% with balanced precision and recall for both positive and negative sentiment categories based on 10-Fold Cross Validation. The results show that negative sentiment is more dominant, mainly related to performance issues and underdeveloped features. These findings serve as a valuable input for future application improvements. This study also demonstrates that the Naïve Bayes method is effective for processing text-based user reviews to support digital service evaluation.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507004428	T179788	T1797882025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1797882025

Publisher

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

Collation

xiii, 104 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

005.360 7

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Sistem informasi

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment