Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Indonesian Journal of Artificial Intelligence and Data Mining International Journal Software Engineering and Computer Science (IJSECS) Malcom: Indonesian Journal of Machine Learning and Computer Science
Irfan Pratama
Mercu Buana university Of Yogyakarta
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Sentiment Analysis of the TikTok Tokopedia Seller Center Application Using Support Vector Machine (SVM) and Naive Bayes Algorithms Faddilla Aulia Dara; Irfan Pratama
International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 1 (2025): APRIL 2025
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v5i1.3463

Abstract

The TikTok Tokopedia Seller Center application is a collaboration between TikTok and Tokopedia designed to help sellers manage their stores and boost sales. Despite offering various features, complaints about poor user experience often appear in reviews on the Google Play Store. This study aims to analyze user sentiment towards the TikTok Tokopedia Seller Center application using a dataset of 2,000 reviews, using the Support Vector Machine (SVM) and Naive Bayes algorithms to classify positive, negative, and neutral sentiments. In addition, this study also attempts to compare the effectiveness of these algorithms in sentiment analysis and evaluate the performance of two weighting methods: TF-IDF and Term Presence. The dataset used was taken by scraping review data on the Google Play Store in Python, as many as 2000 user review datasets. This study found 1,171 negative sentiments, 735 positive sentiments, and 94 neutral sentiments. The results showed that the accuracy of SVM (0.81 and 0.78) was higher than Naive Bayes (0.69 and 0.75). It is hoped that this research can help potential users to find user sentiment towards the application and provide valuable information for application developers to understand user needs and expectations so that developers can improve application features more appropriately and effectively
Comparative Analysis of Random Forest, Explainable Boosting Machine and Ensemble Stacking Performance for Hepatitis C Disease Classification Anastasia Ngeni Bagur; Irfan Pratama
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 6 No. 2 (2026): MALCOM April 2026
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v6i2.2561

Abstract

This study analyzed and compared the performance of three machine learning methods: Random Forest, Explainable Boosting Machine, and a Stacking Ensemble method for Hepatitis C disease classification. The study evaluated the effects of handling extreme values using the interquartile range method and applying class-balancing oversampling to the training data. A dataset of 615 patient samples, categorized into five severity classes, was used. Experiments were conducted across four scenarios: with and without outlier correction, and with and without class balancing. Model performance was assessed using accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve. Results showed that class balancing consistently improved all macro-averaged performance metrics. The combination of Random Forest with oversampling prior to outlier correction achieved the highest F1-score of 0.8086 and an area under the curve of 0.9710. These findings highlighted the importance of addressing class imbalance to improve the recognition of minority classes in clinical datasets and demonstrated the potential of ensemble methods for reliable severity classification in Hepatitis C.
Spice Image Classification Using ResNet50 and Augmentation Technique Julio Francisco Bacun; Irfan Pratama
Indonesian Journal of Artificial Intelligence and Data Mining Vol. 8 No. 3 (2025): November 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

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

Abstract

This research aimed to develop an automatic classification system for Indonesian spices using a deep learning approach based on the ResNet50 architecture. The classification task involved 31 spice categories with 210 images per class. Two training strategies were implemented: training the model from scratch and using transfer learning with pre-trained weights from ImageNet. The model trained from scratch achieved a validation accuracy of 57%, while the transfer learning approach combined with fine-tuning of the last 33 layers resulted in a significantly higher validation accuracy of 96%. Image preprocessing, data augmentation, and class weighting were applied to improve the model’s generalization and handle data imbalance. The confusion matrix analysis showed that most predictions aligned with the true labels, especially in the transfer learning model. These findings demonstrate that transfer learning with ResNet50 can effectively classify spice images with high accuracy, even when visual similarity between certain classes exists. This research highlights the potential of deep convolutional neural networks to support automatic and reliable identification systems for biodiversity mapping and agricultural industries
Co-Authors Anastasia Ngeni Bagur Faddilla Aulia Dara Julio Francisco Bacun