Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Journal of Basic and Applied Science
Ramadhanu Ginting
Politeknik Negeri Medan, Indonesia
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Physics

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Hybrid ABSA–C5.0 framework for interpretable classification of tourist perceptions in digital destination services Fristi Riandari; Ramadhanu Ginting; Indri Sulistianingsih; Virdyra Tasril; Ade Rizka
International Journal of Basic and Applied Science Vol. 15 No. 1 (2026): Basic and Applied Science
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/ijobas.v15i1.856

Abstract

This study proposes an interpretable ABSA–C5.0 hybrid framework for analyzing tourists’ perceptions of digital destination information services. This framework integrates Aspect-Based Sentiment Analysis (ABSA) for aspect extraction and sentiment assessment with C5.0 decision trees for classification and rule generation. This study follows the Knowledge Discovery in Databases (KDD) process, including preprocessing, feature engineering, modeling, and evaluation. The experiment uses a statistically synthesized dataset containing 72 labeled reviews, designed to reflect real-world online review patterns. With a 70:30 validation split, the model achieved 97.22% accuracy and a Cohen’s Kappa value of 0.947 in this controlled setting. However, these results are not intended for generalization, given the limited dataset size, synthetic data construction, and the absence of baseline comparisons and statistical significance tests. The extracted rules indicate that interactivity, clarity, and response speed are the primary factors driving positive perceptions. This framework is suitable for exploratory analysis, while further validation with real-world data and comparative models is required.
Co-Authors Ade Rizka Fristi Riandari Indri Sulistianingsih Virdyra Tasril