Journal of Information System and Artificial Intelligence

The Systems Paradigm in AI Ethics and Infrastructure Governance: An Analysis of the Role of Operating Systems

2026-11-02T20:00:25+07:00

The rapid development of artificial intelligence (AI) has had a transformational impact across various sectors, yet it simultaneously raises multidimensional challenges, particularly in terms of ethics and infrastructure governance. This study aims to analyze AI governance through a system paradigm approach, using the operating system (OS) as an analytical analogy. A qualitative method was employed through a literature review of reputable journals and academic databases addressing AI ethics, the system paradigm, and infrastructure governance. The results show that the system paradigm provides a holistic framework for integrating ethical principles, regulatory mechanisms, and technical functions within the AI ecosystem. The OS analogy highlights the importance of governance components such as an ethical kernel, access control, and security layers to ensure transparency, accountability, and fairness. This study concludes that responsible AI governance requires a systemic, adaptive, and sustainability-oriented approach that bridges technological innovation with social and ethical values.

An IndoBERT-Based Intelligent Chatbot for School Information Services

2026-11-02T20:00:44+07:00

Fragmented school communication can delay access to official information and increase repetitive administrative inquiries. This study developed and evaluated an intelligent school-information website integrated with an Indonesian-language chatbot at MA Islamiyah Bindu. The web application was implemented using PHP, Bootstrap 5, and MySQL, while the chatbot employed the indobenchmark/indobert-base-p1 model for multi-class intent classification. A balanced dataset of 600 school-related utterances covering ten intents was prepared and divided into 500 training and 100 independent test samples. IndoBERT was fine-tuned for 40 epochs using a maximum sequence length of 64 and a batch size of 8. Training loss decreased from 2.4970 to 0.0027, while training accuracy reached 100%. On the held-out test set, the model achieved 94.0% accuracy, 94.3% macro-precision, 94.0% macro-recall, and 94.0% macro-F1. Black-box testing confirmed that all principal website modules, chatbot interactions, controlled response retrieval, and fallback handling operated correctly. The integrated architecture provided accurate, responsive, and centrally managed access to school profiles, schedules, facilities, admission requirements, and contact information.

Leveraging the Internet of Things to Enhance the Security of Two-Wheeled Vehicles

2026-11-02T20:01:47+07:00

This research aims to develop a security system for two-wheeled motor vehicles based on the Internet of Things (IoT), designed to reduce motorcycle theft. The system is built using the ESP32 microcontroller and the NEO-6M GPS module, integrated with an Android application named Motocurity via Bluetooth connection. The system detects vehicle movement based on changes in GPS coordinates, which are then converted into meters. The buzzer will sound when movement exceeds a certain threshold and simultaneously send a notification to the Motocurity Android app. The system development follows the Waterfall methodology, which includes requirement analysis, system design, implementation, and deployment. Testing is carried out using the BlackBox method and usability testing. The BlackBox test results show that all features function correctly, and the usability testing involving 23 respondents yields an average score of 82.8, which falls into the “Good” category, indicating that the system is user-friendly. Therefore, the system can be implemented effectively and has the potential to be further developed with broader connectivity.

Information Gain-Based Feature Selection in Support Vector Machines (SVM) for Tuberculosis Prediction

2026-11-02T20:01:13+07:00

Tuberculosis (TB) is one of the infectious diseases that remains a global health problem, requiring an accurate computational approach to assist in the prediction and clinical decision-making processes. This study aims to evaluate the performance of Support Vector Machine (SVM) in predicting tuberculosis and analyze the contribution of Information Gain (IG)-based feature selection to improving model performance. The dataset used was obtained from the Mendeley public repository and consisted of 493 patient data with 16 encoded attributes. The research stages included data preprocessing, calculation of Information Gain values, selection of relevant features, training of the SVM model with Radial Basis Function (RBF) kernel, and performance evaluation using accuracy, precision, recall, and F1-score metrics. The results of the experiment show that the SVM model without feature selection achieved an accuracy of 0.99, with a recall value of 0.97 for the negative class and 1.00 for the positive class. The application of Information Gain produced identical performance, namely an accuracy of 0.99, a macro-average F1-score of 0.99, and a weighted-average F1-score of 0.99. Confusion matrix analysis, both in absolute and normalized forms, showed a very low classification error rate in both scenarios. These findings indicate that the dataset has highly informative features, so feature selection based on Information Gain is not necessary.

Design and Development of a Web-Based Laravel Application for Library Automation at SMP Muhammadiyah 2 Kartasura

2026-11-02T20:00:59+07:00

The library at SMP Muhammadiyah 2 Kartasura currently relies on inefficient manual management that is prone to data errors. This research aims to develop a web-based library information system using the Laravel framework and MySQL database, employing the Agile development method. The system is designed to automate the management of book data and lending transactions, featuring automatic reminder notifications via WhatsApp API to prevent book loss. Black Box testing on 13 main scenarios demonstrated a 100% success rate in functionality, while an evaluation using the System Usability Scale (SUS) with 36 respondents revealed a positive perception of the system's usability. These results prove that the digital transformation effectively enhances operational efficiency, simplifies librarian tasks, and provides an accurate, user-friendly lending management solution.

Implementation of Enterprise Resource Planning at Chic Boutique Fashion Store

2026-11-02T20:02:00+07:00

In this era filled with many digital-based activities, it indirectly encourages business people to move out of their comfort zone. One of them is the Chic Boutique Fashion Store. The Chic Boutique Fashion Clothes Store is a clothing store that focuses on selling various types of trendy and quality clothing. Chic Boutique has marketed its products online. However, this has not been considered effective because several work systems such as making billing receipts, cashiers, official Seller websites, have not used an adequate ERP system. Therefore, in this study, the application that can overcome the problems that occur is the Odoo ERP application. Odoo is an open source ERP application that can be accessed via a website, which is suitable for use in new companies so that it can reduce costs for the application development process. The modules developed at the Chic Boutique Fashion Store include the Point of Sale Module, Website Module, Invoicing Module, Inventory Module, and Contacts Module

Enhancing Machine Learning Algorithms Using Particle Swarm Optimization (PSO) to Analyze Coffeeshops in Padang City

2026-11-02T20:01:26+07:00

Sentiment analysis of customer reviews is a crucial component in understanding consumer perception of coffeeshop services, especially in Padang City. This study aims to enhance text classification performance by employing two machine learning algorithms, Support Vector Machine (SVM) and Naïve Bayes (NB) and optimizing them using Particle Swarm Optimization (PSO). To address data imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. The dataset consists of customer reviews categorized into three sentiment classes: negative, neutral, and positive. Evaluation results indicate that the optimized SVM+PSO model achieved the highest accuracy of 78.57%, while NB+PSO achieved 73.21%. The implementation of PSO successfully improved the accuracy and f1-score compared to baseline models. This study demonstrates that combining SMOTE and PSO can significantly enhance the performance of multi-class sentiment classification in local business domains such as coffeeshops

Design and Implementation of an Integrated Intelligent System for Online Content Moderation Using AI and Single Sign-On (SSO)

2026-11-02T20:00:06+07:00

The increase in user activity on digital platforms has driven significant growth in the volume of content published in real time. However, this development has also heightened the risk of spreading harmful content such as hate speech, spam, and misinformation, which according to recent studies remains one of the biggest threats in the global digital ecosystem . This research proposes the design and implementation of an integrated intelligent system for online content moderation using Artificial Intelligence (AI) and a Single Sign-On (SSO) mechanism, which has been proven to enhance authentication security and efficiency across various digital platforms since 2022. By applying the Agile methodology, system development is carried out iteratively, enabling rapid adaptation to user needs and behavioral dynamics [4]. The evaluation results show that the integration of AI classification models and SSO can improve the speed of content moderation while strengthening user access security. These findings align with recent research trends emphasizing the importance of automated moderation[5], and unified identity management in maintaining the security of digital spaces.

Customer Relationship Management Implementation at Zidan Salon Yogyakarta

2026-11-02T19:59:52+07:00

Customer Relationship Management (CRM) is an important strategy for building long-term customer relationships, especially in today’s competitive digital landscape. This study aims to assess the impact of implementing a CRM system on customer satisfaction, operational efficiency, and marketing strategies at Zidan Salon Yogyakarta. A qualitative descriptive approach was used, with data collected through observation, interviews, and on-site documentation. The results indicate that implementing CRM enables Zidan Salon to better understand customer needs, manage customer data more effectively, and improve scheduling, communication, and promotion. Data-driven strategies developed from the CRM system have been shown to increase customer loyalty and provide Zidan Salon with a competitive advantage in the highly dynamic beauty industry. This study also identifies challenges in system integration and data management and proposes strategic steps to optimize future CRM implementation.

E-Business Website Design with SWOT and PIECES Analysis Methods at Planet Book Store

2026-11-04T13:10:26+07:00

Planet Book Store is a bookstore in Yogyakarta that sells textbooks and fiction and nonfiction books, but it faces increasing competition from other bookstores and online platforms, and its book collection can only be viewed on social media and search engines. This study aims to design an e-business website for Planet Book Store using a combination of SWOT and PIECES analyses. The research was conducted in several stages: problem identification, literature review, data collection, SWOT analysis of internal and external factors, formulation of SO, ST, WO, and WT strategies, PIECES analysis comparing the old and new systems, definition of system requirements, and website design and implementation. The SWOT analysis identified five strengths, three weaknesses, four opportunities, and five threats, which produced strategies such as selling and renting e-books, offering loyalty programs, focusing on specific market segments, and reducing dependence on physical sales and single distributors. The PIECES analysis showed that the old, largely manual system was slow, provided limited information, increased customer costs, was prone to recording errors, and resulted in less optimal service. Based on these findings, a website was developed with registration and login, a book catalog with price filters, a shopping cart, checkout, and contact features. The study concludes that combining SWOT and PIECES provides a systematic basis for translating business strategies and system weaknesses into concrete website features that can expand the store’s reach, make book information more complete and accessible, and improve the efficiency of the ordering process.