cover
Contact Name
Mesran
Contact Email
jurnal.josh@gmail.com
Phone
+6282161108110
Journal Mail Official
jurnal.josh@gmail.com
Editorial Address
Sekretariat Forum Kerjasama Pendidikan Tinggi (FKPT) Jalan Sisingamangaraja No. 338, Medan, Sumatera Utara
Location
Kota medan,
Sumatera utara
INDONESIA
JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH)
ISSN : -     EISSN : 2686228X     DOI : -
Core Subject : Science,
Artikel yang dimuat melalui proses Blind Review oleh Jurnal JOSH, dengan mempertimbangkan antara lain: terpenuhinya persyaratan baku publikasi jurnal, metodologi riset yang digunakan, dan signifikansi kontribusi hasil riset terhadap pengembangan keilmuan bidang teknologi dan informasi. Fokus Journal of Information System Research (JOSH)
Articles 795 Documents
Prediksi Curah Hujan Jawa Barat Menggunakan Algoritma Machine Learning: Analisis Komparatif Berbasis Data Badan Meteorologi, Klimatologi, dan Geofisika (BMKG) 2024 Fahmi, Alif; Amali, Amali; Badruzzaman, Aceng
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9018

Abstract

West Java Province exhibits high vulnerability to hydrometeorological disasters due to dynamic rainfall variability, necessitating an accurate weather prediction system for effective disaster mitigation.1 This study aims to conduct a comparative performance analysis of Machine Learning algorithms, specifically Support Vector Machine (SVM), Naïve Bayes, Random Forest, and XGBoost, in predicting rainfall events based on 2024 daily meteorological data sourced from BMKG. Through computational experiments utilizing three data splitting scenarios 80:20, 75:25, and 70:30, and Recursive Feature Elimination (RFE), the results demonstrate that Naïve Bayes, Random Forest, and XGBoost consistently achieved a perfect accuracy of 100% across all scenarios, whereas SVM exhibited stable but more conservative performance with an average accuracy of 95.4%. In-depth analysis indicates that the absolute accuracy achieved under specific data conditions was significantly influenced by the dominance of the daily rainfall feature (RR), leading to indications of data leakage where ensemble and probabilistic models exploited deterministic relationships much more effectively than SVM. Consequently, this study recommends a rigorous re-evaluation of input features, prioritizing atmospheric leading indicators, to develop a more realistic and adaptive early warning system in the future.
Analisis Spasial Faktor Ekonomi dan Pendidikan terhadap Angka Putus Sekolah Dasar di Indonesia dengan Pendekatan Algoritma Geographically Weighted Regression Azraf, Faiz; Permana, Farhan Cahya; Ayyash, Muhammad Al Fathi; Rinawan, Nadzira Rifqi Amin; Putra, Ravelin Lutfhan Syach
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9033

Abstract

The elementary school dropout rate remains a significant educational problem in Indonesia, with varying characteristics across regions. This study analyzes the influence of socioeconomic and educational factors on the elementary school dropout rate in Indonesia in 2023 using a spatial approach. The variables used include poverty level, per capita expenditure, average length of schooling, and expected length of schooling, with 34 provinces as the analysis unit. The analytical methods used were Ordinary Least Squares (OLS) and Geographically Weighted Regression (GWR). OLS analysis was used as an initial comparison before applying the location-based model. The results showed that OLS had low explanatory power, while GWR was able to capture spatial variation and heterogeneity in the influence of variables across provinces. These findings suggest that a spatial approach is more relevant in analyzing the elementary school dropout problem and can serve as a basis for formulating policies that are more appropriate to regional characteristics. The purpose of this study is to evaluate the spatial influence of the following variables: poverty level, per capita expenditure, Mean Years of Schooling (RLS), and Expected Years of Schooling (HLS) on elementary school students in 34 provinces in Indonesia, and to examine the accuracy level of the Geographically Weighted Regression (GWR) model compared to the Ordinary Least Squares (OLS) model. The results of this study confirm that the determinants of school dropout are local and vary between provinces, so that the implications of government policies must be designed specifically on an inter-regional basis, rather than being made nationally average.
Sistem Informasi Stok Seragam Berbasis Android sebagai Solusi Pengelolaan Persediaan Toko dengan Menggunakan Metode Prototype Alda, Muhamad; Hanafi Harianja, Dio Arif; Putra Siregar, Armansyah; Septiawan, Muhammad Angga; Ramadhan, M. Rizky
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9081

Abstract

Retail business management requires systems that are capable of providing accurate and timely information, particularly in managing inventory, such as in school uniform stores. Poor inventory monitoring may lead to various problems, including stock discrepancies, recording errors, and difficulties in obtaining up-to-date inventory information. At Toko Seragam Faiz, the management of uniform stock for elementary, junior high, and senior high schools is still performed manually, which has not yet supported efficient and accurate inventory control. Therefore, this study aims to design and develop an Android-based Uniform Stock Information System as a solution for inventory management at Toko Seragam Faiz. The system is designed to manage product and stock data in an integrated manner, enabling fast and accurate access to inventory information through mobile devices. The system development employs the prototyping method, which involves direct user participation during the design process to ensure that the developed system meets operational requirements. The results of this study are expected to assist store owners and staff in monitoring uniform stock more effectively, improving inventory management efficiency, and minimizing stock recording errors.
Perbandingan Kinerja Algoritma Machine Learning dalam Klasifikasi Sentimen Komentar Publik terhadap Pelayanan Perpajakan Kurniawan, Dadang; Gata, Windu; Asra, Taufik
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9164

Abstract

Early identification of malignant transformation in oral leukoplakia is crucial to prevent progression to Oral Squamous Cell Carcinoma (OSCC). However, conventional clinical assessment still faces limitations in terms of accuracy and interpretability, highlighting the need for reliable and transparent predictive approaches. This study aims to evaluate the performance of interpretable machine learning models in predicting malignant transformation of oral leukoplakia and OSCC based on clinical and histopathological data. A retrospective dataset consisting of 237 patient medical records was analyzed using several interpretable models, including Explainable Boosting Machine (EBM), Generalized Additive Models (GAM), and Symbolic Regression, and compared with black-box models such as Random Forest and Deep Neural Network. Model performance was evaluated using accuracy, sensitivity, specificity, and area under the curve (AUC). The results demonstrate that interpretable models achieve competitive predictive performance compared to black-box models while offering superior transparency and interpretability. Feature contribution analysis indicates that histopathological characteristics are the most influential factors in malignancy prediction. These findings suggest that interpretable machine learning models have strong potential as clinical decision support systems for early oral cancer detection.
Optimasi Support Vector Machine Menggunakan Pendekatan Hybrid Kernel Linear-RBF Untuk Klasifikasi Penyakit Jantung Mulyadi, Mulyadi; Kasoni, Dian; Handayani, Nurdiana; Liesnaningsih, Liesnaningsih
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9174

Abstract

Heart disease remains one of the leading causes of mortality worldwide, making early detection crucial to prevent severe complications. The limitations of conventional diagnostic approaches have encouraged the adoption of machine learning techniques to enable faster and more accurate predictions. Support Vector Machine (SVM) is widely recognized as an effective method for medical classification tasks; however, its performance is highly dependent on the choice of kernel function. This study evaluates three single-kernel SVM models (Linear, RBF, and Polynomial) and two hybrid kernel configurations, namely Linear–RBF and Linear–Polynomial, using the UCI Heart Disease Statlog dataset, which consists of 270 samples and 13 predictive features. In the hybrid approach, the probabilistic outputs of the individual base kernels are combined through an aggregation strategy to construct a decision function capable of capturing both linear and nonlinear patterns simultaneously. To ensure performance stability on the relatively small dataset, model evaluation was conducted using Stratified K-Fold Cross Validation, ensuring that the reported results do not rely on a single data split. Experimental results indicate that the SVM-Polynomial model achieved the highest ROC-AUC value of 0.9420; however, it did not outperform other models in terms of accuracy, precision, or F1-score. The hybrid approach demonstrated more consistent overall performance, with the Linear–RBF combination emerging as the best-performing model, achieving an accuracy of 0.8889, macro precision of 0.8896, and macro F1-score of 0.8886. These findings suggest that integrating linear and nonlinear kernel characteristics produces a more balanced decision function compared to single-kernel models. In contrast, the Linear–Polynomial combination did not yield significant performance improvements. The main contribution of this study lies in presenting a structured comparative analysis of kernel combination strategies in SVM for heart disease classification, which may support the development of more adaptive and stable clinical prediction systems.
Komparasi Ekstraksi Fitur TF-IDF dan Word2Vec pada Naïve Bayes untuk analisis Sentimen Pembangunan IKN di YouTube Rahmad Fahrozi, Mu. Aldi; Siswa, Taghfirul Azhima Yoga; Verdikha, Naufal Azmi
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9198

Abstract

The development of Indonesia’s New Capital City (IKN) has generated diverse public responses on social media, particularly YouTube, making sentiment analysis necessary to map public perceptions. Previous studies have reported relatively low classification accuracy, reaching only 60%, indicating the need for more effective approaches to improve performance. This study aims to compare the performance of the Naïve Bayes algorithm in classifying public sentiment toward the IKN development using two feature extraction methods, namely TF-IDF and Word2Vec. The data were collected from YouTube comments and processed through preprocessing stages, expert-based labeling, and evaluation using 10-Fold Cross Validation. The results show that the TF-IDF-based Multinomial Naïve Bayes model achieves the best performance with an accuracy of 83%, a positive recall of 82%, and a negative F1-score of 85%, outperforming the Word2Vec-based Gaussian Naïve Bayes model, which attains an accuracy of 82% with a lower positive recall of 76%. These findings confirm that TF-IDF is more effective and stable in handling short-text comment characteristics than Word2Vec, which requires a larger corpus for optimal semantic representation.
Gamified Student Activity Transcript System using MDA Framework Nursetyo Reginanda, Ezekiel Pradipta; Saputra, Wahyu Andi; Wardhana, Ariq Cahya; Adhitama, Rifki
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9199

Abstract

Universities increasingly recognize that employability and civic competencies are formed not only through formal coursework but also through co-curricular and extracurricular engagement. In many campuses, however, activity reporting remains fragmented, highly manual, and submitted late, which results in verification bottlenecks and incomplete student records. This study develops a web-based Student Activity Transcript (SAT) application to support end-to-end submission, verification, and accumulation of student activity points. A gamification approach is embedded to reduce reporting friction and sustain participation. The design follows the Mechanics–Dynamics–Aesthetics (MDA) framework so that each game element is justified from rules to run-time interaction patterns and the intended user experience. The system is implemented using a PHP web framework and a relational database, and it integrates role-based workflows for students, academic advisers, and student affairs administrators. Functional validation is performed through specification-based (black-box) testing to confirm that critical workflows—registration, login, activity submission, verification, and transcript generation—operate as intended. The resulting artifact demonstrates a reusable pattern for universities that need to digitize activity transcripts while ensuring that gamification is applied in a structured, theory-informed manner. This work contributes to TAK governance workflow that preserves institusional verification while adding engagement loops, and an implementation and test blueprint that can be adapted to other campuses adopting transcript or digital badge recognition system.
Rancang Bangun Aplikasi E-commerce Berbasis Web Menggunakan Metode Waterfall Ramadhanti, Aisyah Isnaeni; Hanif, Isa Faqihuddin
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9212

Abstract

Dunia Anak Store currently still applies conventional marketing systems and manual recording, which results in limited market reach and inaccuracies in stock data. This research aims to develop a web-based sales information system to address these issues using the waterfall method. The development stages include requirements analysis, system design, implementation, and testing. System testing was carried out in two phases: alpha testing to validate functionality, and beta testing involving direct users to measure system feasibility. The results of alpha testing showed that all features functioned correctly according to the design, while beta testing indicated that the system was well accepted by users. In conclusion, this system successfully improved transaction efficiency, expanded promotional reach, and resolved stock data accuracy problems at Dunia Anak Store.
Implementasi Dashboard Real-Time Untuk Memantau Proses Pendaftaran Webinar Berbasis Website Prasetyo, Adji; Halim, Zuhri
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9214

Abstract

This research aims to develop a web-based information system with an analytical dashboard to improve business process efficiency and campaign evaluation. The research method employs the Waterfall model. The system is developed with a centralized database and is equipped with a data visualization dashboard using Microsoft Power BI, divided into Revenue and Activity pages. The implementation results in a functional website for webinar registration integrated with the database. Alpha and beta testing shows that the system operates according to expected functionality, has an easy-to-understand interface, and assists the registration and monitoring processes. Based on data from 20 user respondents, this registration website system has successfully achieved a very high level of acceptance and satisfaction. An overwhelming majority of respondents (90% to 100%) rated the website as responsive, fast, very helpful, easy to understand, and providing a good impression. Although there is slight room for improvement in operational ease (with 35% stating it is not difficult, while the remainder were possibly neutral or disagreed), the overall survey results prove that this system functions very effectively as a decision-support tool for management, as well as a successful and positive medium for interaction with prospective registrants. It is concluded that this system has successfully become an effective decision-support tool for management through periodic reporting.
Analisis Ketahanan Variational QNN Terhadap Bit Flip dan Depolarizing Noise Pada Subset Dataset MNIST Sinaga, Gionathan Advent Kristianto; Berutu, Suneng Sandino; Astuti, Aninda
Journal of Information System Research (JOSH) Vol 7 No 2 (2026): January 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v7i2.9226

Abstract

The advancement of quantum computing has encouraged the use of Variational Quantum Neural Networks (VQNNs) as an alternative approach for data classification tasks. However, the implementation of VQNNs in the Noisy Intermediate-Scale Quantum (NISQ) era still faces major challenges due to quantum noise, which can significantly degrade model performance. This study aims to analyze the robustness of VQNNs against quantum noise in a binary classification task using a subset of the MNIST dataset. Image data are processed through normalization and dimensionality reduction using Principal Component Analysis (PCA), and subsequently encoded into quantum circuits using the angle encoding method. The VQNN model is designed with six qubits and a single variational layer, and evaluated under two conditions: an ideal quantum simulation (before noise, statevector) and a noisy quantum simulation (after noise). Quantum noise is simulated using Qiskit Aer, considering two types of noise, namely bit flip and depolarizing noise, across various probability levels. Experimental results show that under ideal conditions, the VQNN achieves a test accuracy of 85.2%. However, increasing noise probabilities lead to a gradual degradation in performance, approaching the random classification threshold at high noise levels. Bit flip noise causes a more severe performance decline compared to depolarizing noise. These findings confirm that quantum noise is a critical factor affecting the stability of VQNNs and highlight the importance of developing effective noise mitigation strategies for VQNN implementations in the NISQ era.