Article Per Year (5 Year)
p-Index From 2021 - 2026
0.702
P-Index
This Author published in this journals
All Journal JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Bulletin of Computer Science Research
Adityo Permana Wibowo
Universitas Teknologi Yogyakarta, Sleman
Computer Science & IT Decision Sciences, Operations Research & Management

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

Found 4 Documents
Search

 1 
Kinerja Metode Fine-Tuning IndoBERT untuk Klasifikasi Emosi Multi-Kelas pada Teks Informal Bahasa Indonesia Haikal Fawwaz Karim; Adityo Permana Wibowo
Bulletin of Computer Science Research Vol. 6 No. 1 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v6i1.850

Abstract

Automatic emotion analysis on informal Indonesian texts is a challenging task due to high linguistic variation, the use of slang, and abbreviations. This research focuses on the development and evaluation of an accurate emotion classification model, which can serve as a core component various relevant Natural Language Processing (NLP) applications. The proposed method is the fine-tuning of the pre-trained language model IndoBERT to classify texts from the social media platform Twitter (X) into five emotion classes: anger, fear, happy, love, and sadness. A custom dataset consisting of 4,940 Twitter posts was built through a targeted scraping process and statistically validated labeling to ensure data relevance and balance. Experiments show that after undergoing a comprehensive text preprocessing stage, including normalization using a custom abbreviation dictionary and stemming, the fine-tuned model achieved very high performance. Evaluation results on the test data show the model successfully reached an accuracy of 94% and a weighted average F1-score of 0.94. Learning curve analysis also confirms that the model did not suffer from overfitting and possesses good generalization capabilities. These results demonstrate that the IndoBERT fine-tuning approach is a highly effective and reliable solution for emotion classification in the informal Indonesian text domain.
Klasifikasi Jenis Madu Akasia dan Madu Hutan Berdasarkan Warna RGB Menggunakan Metode Multilayer Perceptron Ridwan Halim; Adityo Permana Wibowo
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): January 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6366

Abstract

The advancement of technology has driven the agricultural industry to become more advanced and modern. Distinguishing honey with nearly identical colors is a challenging task. However, The ability to differentiate the color of acacia and forest honey is the simplest approach to ensuring the authenticity and quality of honey products. This study aims to develop a honey color classification model using Multilayer Perceptron (MLP). Image data were collected from various angles under natural lighting, followed by ninety experiments using parameter combinations, including data imbalance handling methods, dense layer structures, and training settings. The results showed that the MLP model with an optimal configuration, utilizing the Adaptive Synthetic Sampling (ADASYN) method for data imbalance, achieved a validation accuracy of 90.63%. This accuracy highlights the potential of the model to support industrial automation processes in reliably distinguishing honey colors.
Implementasi Model Waterfall dalam Aplikasi Manajemen Keuangan Berbasis Android Niko Fernanda; Adityo Permana Wibowo
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): January 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6370

Abstract

One of the main components in maintaining the stability and financial well-being of people and families is effective financial management. The myth that expenses will always increase along with income is one of the common misconceptions in society. This study aims to address this by creating financial management software for Android that facilitates effective and efficient financial management for users. The research methodology uses the waterfall model, which means that every step from needs analysis to implementation is completed systematically. The development process of this application utilizes Android Studio with the Kotlin programming language which is known to be efficient, while MySQL is used as a database for secure financial information management. The application system is designed using the Unified Modeling Language (UML) to define workflows and processes in a structured manner. The results of the application test use the blackbox testing method to test this application to ensure that all features such as recording financial information, income and expense transactions, and creating financial reports function as they should. In addition, this application also provides additional features in the form of investments to help users monitor their investment assets. From the tests carried out, all application features showed a success rate of 100%, indicating that the application functions according to the designed specifications. This application allows users to optimize financial management, so they can improve their standard of living in a more planned and systematic way.
Marketplace Pemasaran Produk Pertanian Berbasis Mobile Menggunakan Pendekatan Waterfall Asyhar Qowiim; Adityo Permana Wibowo
Journal of Information System Research (JOSH) Vol 6 No 2 (2025): January 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i2.6484

Abstract

The current agricultural industry is still minimal in utilising technology so that limited access to information related to market demand and means of direct sales to consumers is a major obstacle in improving the welfare of farmers. The distribution process of agricultural products is still carried out conventionally through direct interaction, making it less effective and efficient. The development of information and communication technology, especially in the use of mobile devices, provides new opportunities to overcome existing problems. This research aims to solve the existing problems by creating a mobile-based application to increase sales of agricultural products. The application is developed using the waterfall approach method with several stages such as needs analysis, design, implementation, testing to maintenance. Flutter programming language is also used in coding the application system. Based on the design and implementation carried out in this study, an application is produced with features that display products and effective payment features. The existing features are then tested by 30 respondents with the black box testing method and the results obtained are 100% the application can run well. The application can increase transparency and efficiency in the sale of agricultural products. The application also provides convenience for farmers as consumers.
Co-Authors Asyhar Qowiim Haikal Fawwaz Karim Niko Fernanda Ridwan Halim