Article Per Year (5 Year)
p-Index From 2020 - 2025
0.702
P-Index
This Author published in this journals
All Journal Indonesian Journal of Information System JOURNAL OF APPLIED INFORMATICS AND COMPUTING INOVTEK Polbeng - Seri Informatika
Ozzi Suria
Unknown Affiliation
Computer Science & IT

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Public Sentiment Analysis of Danantara Policy through Social Media X Using SVM and Random Forest Djema, Gayus Gregorius Ferdinand; Ozzi Suria
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/rcr21h75

Abstract

Abstract - This study aims to analyze public sentiment toward the establishment of the Danantara Investment Management Agency (Danantara) through the X social media platform (formerly Twitter) using a machine learning-based text classification approach. While sentiment analysis has been widely applied across various domains, there remains a research gap in examining public responses to new national policies particularly Danantara on platform X. A total of 1,713 tweets were collected using Python-based web scraping via Google Colab during the period from February to June 2025. The research involved data preprocessing, manual sentiment labeling, model training using Support Vector Machine (SVM) and Random Forest algorithms, and performance evaluation using metrics such as accuracy, precision, recall, and F1-score. The classification results show that positive sentiment dominates at 55.6%, while negative sentiment accounts for 44.4%. Random Forest outperformed SVM with an accuracy of 92.36% and an F1-score of 92.19%, compared to SVM's accuracy of 85.45% and F1-score of 87.54%. These findings indicate that Random Forest is more effective in handling short-text public opinion data that is often unstructured. Practically, this study recommends the integration of real-time sentiment monitoring through social media as a strategic tool for policymakers and state-owned enterprises (SOEs) in formulating more responsive and data-driven public policies
Instagram-Based Sentiment Analysis on the Oil Refinery Project in Batam Using SVM and XGBoost Rumapea, Doni Immanuel; Ozzi Suria
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/am1zxb64

Abstract

This sentiment analysis of Instagram comments regarding the planned construction of an oil refinery in Batam classifies public opinion into three categories: positive, neutral, and negative. The initial dataset of 1,576 comments was reduced to 1,441 after text preprocessing (tokenization, stop‑word removal, and stemming), and then split into 1,152 training instances and 289 testing instances. Two machine learning algorithms, Support Vector Machine (SVM) with class_weight='balanced' and Extreme Gradient Boosting (XGBoost) with oversampling, were applied to address class imbalance. In addition to accuracy (SVM: 81.25%; XGBoost: 96%), precision, recall, and F1‑score metrics were evaluated to assess the balance between true‑positive and true‑negative classifications. The results indicate that XGBoost not only outperformed SVM in terms of accuracy but also achieved the highest F1‑score on the minority class, demonstrating its ability to detect negative opinions that have often been overlooked. This study offers a novel contribution to Instagram-based sentiment analysis a platform that is visually distinct from Twitter by focusing on public opinions surrounding the strategic issue of energy infrastructure development. The findings can be utilized for real-time sentiment mapping, supporting policy formulation, urban planning, and monitoring industry responses to critical projects in the digital era.
Comparative Analysis of ResNet50V2, ResNet152V2, and MobileNetV2 Architectures in Monkeypox Classification Mustaqim, Habi Jiyan; Ozzi Suria
Journal of Applied Informatics and Computing Vol. 9 No. 4 (2025): August 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i4.9756

Abstract

Convolutional Neural Networks (CNN) are recognized for their high accuracy in image classification, but large-scale datasets and significant computer resources are needed to train them from scratch, though. Transfer learning offers a practical solution by leveraging pre-trained models to accelerate training even when data is limited. Although CNNs have been widely applied to skin disease classification, specific evaluations of architectures such as ResNet50V2, ResNet152V2, and MobileNetV2 for monkeypox image classification remain scarce. Therefore, this study aims to comprehensively compare the effectiveness and trade-offs of these architectures in detecting monkeypox through transfer learning. The evaluation focuses on balancing accuracy and computational efficiency across stages, including data collection, preprocessing, model design, training, and testing. The dataset, obtained from Kaggle, consists of 2,310 images across four classes: monkeypox, chickenpox, measles, and normal. Transfer learning was implemented using fine-tuned weights from ImageNet. According to the results, ResNet152V2 needed the most training time but had the lowest loss and the greatest validation accuracy (98.28%). ResNet50V2 maintained a good compromise between accuracy (97.84%) and training efficiency, while MobileNetV2 yielded the best overall classification metrics (97.86% for accuracy, precision, recall, and F1-score), indicating strong generalization. These findings highlight the distinct strengths of each model, offering insights into architecture selection based on specific operational constraints and goals.
Optimizing Sentiment Analysis of Hotel Reviews Using PCA and Machine Learning for Tourism Business Decision Support PRASETYANINGRUM, PUTRI TAQWA; Norshahila Ibrahim; Ozzi Suria
Indonesian Journal of Information Systems Vol. 8 No. 1 (2025): August 2025
Publisher : Program Studi Sistem Informasi Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Sentiment analysis of hotel reviews provides valuable insights for improving customer satisfaction and service quality in the tourism industry. However, the high dimensionality and unstructured nature of review data pose challenges in extracting meaningful insights. This study optimizes sentiment analysis by applying Principal Component Analysis (PCA) for dimensionality reduction and utilizing machine learning models for classification. The proposed approach involves data preprocessing, feature selection using PCA, model training, and performance evaluation. Experimental results show that PCA enhances classification accuracy and computational efficiency by eliminating redundant features, improving sentiment prediction. The comparative analysis demonstrates that the Voting classifier achieves the highest accuracy (95.29%) and F-score (97.50%), while the BiLSTM-FNN model attains the highest recall (99.95%). These findings highlight the potential of PCA-based sentiment analysis in supporting data-driven decision-making for hotel management, enabling enhanced service quality, improved customer experience, and effective marketing strategies.
Co-Authors Djema, Gayus Gregorius Ferdinand Mustaqim, Habi Jiyan Norshahila Ibrahim Prasetyaningrum, Putri Taqwa Rumapea, Doni Immanuel