Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Journal of Information Systems and Informatics Jurnal Ilmiah Sistem Informasi dan Ilmu Komputer
Dian Novianto
Institut Sains dan Bisnis Atma Luhur
Computer Science & IT Industrial & Manufacturing Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Comparative Sentiment Analysis of Profits Anywhere Application Reviews Using KNN and Naïve Bayes Yurindra; Chandra Kirana; Dian Novianto; Tri Sugihartono; Muhammad Ilham
Journal of Information System and Informatics Vol 8 No 4 (2026): August
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i4.1658

Abstract

User reviews on Google Play Store provide valuable information regarding application service quality and user satisfaction. This study aims to compare the performance of the K-Nearest Neighbor (KNN) and Naïve Bayes algorithms for sentiment analysis of reviews of the Profits Anywhere application, a digital business platform offering affiliate marketing and financial services. A total of 1,037 reviews were collected through web scraping and subsequently underwent data cleaning and validation, resulting in 957 valid reviews used in the analysis, consisting of 674 positive and 283 negative reviews. The dataset was subjected to a comprehensive text preprocessing pipeline, including text cleaning, case folding, tokenization, stopword removal, and stemming, followed by feature representation using the Term Frequency–Inverse Document Frequency (TF-IDF) technique. The data were partitioned using an 80:20 stratified train–test split, while hyperparameter optimization was conducted using GridSearchCV with 5-fold stratified cross-validation. Experimental results demonstrate that KNN outperformed Naïve Bayes on the evaluated dataset and experimental configuration, achieving an accuracy of 92.19%, weighted precision of 92.23%, weighted recall of 92.19%, and weighted F1-score of 92.21%. In contrast, Naïve Bayes achieved an accuracy of 88.54%, weighted precision of 89.04%, weighted recall of 88.54%, and weighted F1-score of 88.70%. These findings provide empirical evidence regarding algorithm selection for sentiment analysis of application reviews in the fintech and digital business domains.
Perbandingan Kinerja Model XGBoost dan IndoBERT untuk Deteksi Teks Hoax Terselubung Berbahasa Indonesia Dian Novianto; Lukas Tommy; Sujono Sujono; Yohanes Setiawan Japriadi
Jurnal ilmiah Sistem Informasi dan Ilmu Komputer Vol. 6 No. 2 (2026): Juli: Jurnal Ilmiah Sistem Informasi dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/juisik.v6i2.2411

Abstract

The rapid advancement of Generative AI driven by Large Language Models (LLMs) has raised significant concerns regarding the integrity of digital information. Although text detection systems are evolving rapidly, the majority of current instruments predominantly support English, thereby leaving a substantial research gap in low-resource languages such as Indonesian. This study aims to conduct a comparative performance analysis between XGBoost and IndoBERT for detecting Indonesian text generated by Generative AI. Experiments were executed using a structured, hand-crafted dataset spanning three main domains: Science and Technology, Social and Culture, and Politics. The XGBoost model was evaluated utilizing Term Frequency-Inverse Document Frequency (TF-IDF) feature extraction, whereas IndoBERT relied on bidirectional contextual semantic understanding. The evaluation results on the controlled dataset demonstrated that both architectures achieved perfect accuracy (100%). However, under a stress test employing adversarial trap sentences designed with keyword stuffing techniques, the performance of the two models exhibited a sharp contrast. The global accuracy of XGBoost plummeted drastically to 50.00% because the TF-IDF representation failed to recognize the core logical essence of the sentences and was easily misled by the dominance of individual statistical keywords. Conversely, IndoBERT proved to be more robust by maintaining a global accuracy of 66.67% and recording maximum Precision, Recall, and F1-Score (1.000000) within the Social and Culture class. This demonstrates the capability of the Self-Attention Mechanism in capturing latent context and complex linguistic structures. The implications of these findings emphasize that in countering advanced text manipulation (covert hoaxes), the deployment of context-based models like IndoBERT is far more reliable. Nevertheless, architectural selection must remain dynamically aligned with local computing infrastructure capacity.
Co-Authors Chandra Kirana Lukas Tommy Muhammad Ilham Sujono Tri Sugihartono Yohanes Setiawan Japriadi Yurindra