Skripsi

KNOWLEDGE DISCOVERY MELALUI ANALISIS SENTIMEN BERBASIS ASPEK PADA ULASAN PENGGUNA BYOND BY BSI

---

BYOND by BSI is the latest application developed from BSI Mobile by Bank Syariah Indonesia as part of its digital banking transformation. The quality of this application can be evaluated through user reviews on the Google Play Store; however, the large volume of reviews creates challenges in extracting meaningful information. This study applies an Aspect-Based Sentiment Analysis (ABSA) approach to understand user perceptions of BYOND by BSI based on three main aspects: interface, features and performance, and services. The reviews were collected and processed through several stages, including text preprocessing, keyword-based aspect identification, sentiment labeling using the IndoBERT model, TF-IDF feature extraction, and data balancing with the SMOTE technique. Sentiment classification was conducted using three machine learning algorithms: Naïve Bayes, Support Vector Machine (SVM), and Random Forest. The evaluation results indicate that SVM achieved the most optimal performance among the three models, with an accuracy of 0.95, precision of 0.89, recall of 0.94, F1-score of 0.92, and AUC-ROC of 0.9808. The aspect-based sentiment analysis further shows that the features and performance aspect received the highest number of negative reviews (1166), indicating that users’ main complaints are related to feature reliability and application stability. These findings are expected to provide insights and support decision-making for improving the quality of the BYOND by BSI application.

---

Availability

Detail Information

Series Title

-

Call Number

T1893962025

Publisher

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

Collation

xvii, 96 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
Analisis Sentimen--Proses Data

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment