Text

ASPECT-BASED SENTIMENT ANALYSIS (ABSA) WONDR BY BNI MENGGUNAKAN CNN, LSTM, SVM, DAN NAIVE BAYES

---

Penilaian

---

Wondr by BNI is a banking innovation since its launch in July 2024, has garnered widespread user attention with millions of downloads and thousands of reviews. These user reviews can be thoroughly analyzed using an Aspect-Based Sentiment Analysis (ABSA) approach. This study aims to apply ABSA to reviews of the Wondr app, focusing on four key aspects of usability according to Nielsen: learnability, efficiency, error, and satisfaction. A total of 5,500 review data points were analyzed using CNN, LSTM, SVM, and Naive Bayes algorithms, with feature extraction via Word2Vec. The study results show that the error aspect is the most frequently discussed by users, with the majority of sentiments being negative. Conversely, the satisfaction aspect is dominated by positive sentiments. From the model performance evaluation, the CNN model demonstrated the best overall performance, with the highest accuracy and F1-score across most aspects, and effectively leveraged Word2Vec representations to understand the context of user reviews. The LSTM model showed slightly lower performance than CNN. SVM delivered good results, while the Naive Bayes model consistently showed the lowest performance.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507002865	T173512	T1735122025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1735122025

Publisher

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

Collation

xiii, 131 hlm.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

005.360 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem informasi

Specific Detail Info

-

Statement of Responsibility

EM

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment