Skripsi

ASPECT-BASED SENTIMENT ANALYSIS DAN KNOWLEDGE EXTRACTION UNTUK EVALUASI PERSEPSI KEAMANAN PADA APLIKASI DOMPET DIGITAL

---

The rapid growth of digital wallet usage in Indonesia has raised concerns regarding user security and account protection. This study evaluates user sentiment related to the security features of the DANA digital wallet by applying Aspect Sentiment Classification (ASC), a subtask of Aspect-Based Sentiment Analysis (ABSA). A total of 4,846 security-related reviews were collected using keyword-based filtering, complemented by 3,000 non-filtered DANA reviews and 3,000 GoPay reviews for robustness evaluation. Sentiment labeling was conducted using a hybrid rule-based and manual validation approach, achieving 0.8504 accuracy and a Cohen’s κ of 0.951, indicating near-perfect agreement. Five models—Support Vector Machine (SVM), Random Forest (RF), Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (BiLSTM), and IndoBERT—were evaluated using 5-fold stratified cross-validation. IndoBERT outperformed all models with 98% accuracy, a 0.974 F1-score, and a 0.996 AUC-ROC. Robustness analysis demonstrated that IndoBERT maintained strong generalization across temporal and cross-domain datasets. The sentiment outputs were formatted using XML to support structured knowledge extraction and facilitate integration with analytical systems. This study provides fine-grained insights into user security perceptions and contributes to the development of data-driven decision-making frameworks in the fintech domain. Keywords: Aspect-Based Sentiment Analysis (ABSA), Digital Security, Sentiment Classification, Knowledge Extraction

---

Availability

Detail Information

Series Title

-

Call Number

T1894112025

Publisher

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

Collation

xvii, 101 hlm.; ilus.; tab, 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.310 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Informasi
Pembelajaran Mesin--Analisis Data

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment