cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Muhammad Wali
Contact Email
muhammadwali@amikindonesia.ac.id
Phone
+6285277777449
Journal Mail Official
ijsecs@lembagakita.org
Editorial Address
Jl. Teuku Nyak Arief No. 7b 23112, Kota Banda Aceh, Banda Aceh, Provinsi Aceh
Location
,
INDONESIA
International Journal Software Engineering and Computer Science (IJSECS)
Published by Lembaga Komunitas Informasi Teknologi Aceh
ISSN : 27764869     EISSN : 27763242     DOI : https://doi.org/10.35870/ijsecs
Core Subject : Science,
Computer Science & IT
IJSECS is committed to bridge the theory and practice of information technology and computer science. From innovative ideas to specific algorithms and full system implementations, IJSECS publishes original, peer-reviewed, and high quality articles in the areas of information technology and computer science. IJSECS is a well-indexed scholarly journal and is indispensable reading and references for people working at the cutting edge of information technology and computer science applications..
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 535 Documents
 50   51   52   53   54 
Public Sentiment Analysis of the #KaburAjaDulu Hashtag Using a Combination of Support Vector Machine (SVM) and Random Forest Algorithms Muhammad Derry Oktaviandi; Yuma Akbar; Mesra Betty Yel
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 3 (2026): DECEMBER 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i3.8068

Abstract

This study aims to analyze public sentiment toward the #KaburAjaDulu hashtag on platform X and compare the classification performance of Support Vector Machine (SVM), Random Forest, and a Voting Classifier ensemble. A total of 1,502 posts were collected via web scraping. The text preprocessing pipeline comprised case folding, text cleaning, tokenization, stopword removal, and stemming using the Sastrawi library. Processed texts were transformed into numerical feature vectors using Term Frequency-Inverse Document Frequency (TF-IDF), followed by an 80:20 train-test split. The empirical distribution revealed an extreme class imbalance: negative sentiment dominated at 96.54% (1,450 posts), followed by neutral at 3.33% (50 posts) and positive at 0.13% (2 posts), generating an imbalance ratio of 725:1. SVM and Random Forest achieved identical aggregate scores with 95.35% accuracy, 90.91% precision, 95.35% recall, and a 93.08% F1-score; however, both completely failed to detect neutral and positive classes. The Voting Classifier achieved the highest aggregate performance, reaching 96.01% accuracy, 95.84% precision, 96.01% recall, and a 94.55% F1-score by successfully identifying two neutral instances. Nevertheless, the ensemble model was unable to recognize positive sentiment, yielding zero sensitivity for the extreme minority class. These findings demonstrate that combining SVM and Random Forest offers marginal improvements in aggregate metrics but remains constrained by data distribution. Consequently, relying solely on aggregate accuracy produces misleading evaluations in severely skewed datasets, emphasizing the necessity of per-class metrics, confusion matrices, and data-balancing strategies for social media sentiment classification.
A Study of Cybersecurity Awareness among University Information and Communication Technology Staff in Kabul Abdul Hameed Himat; Sayed Elham Sadat; Mohammad Kabir Ahmadi
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 3 (2026): DECEMBER 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i3.8075

Abstract

This study evaluated cybersecurity awareness among ICT staff in universities in Kabul, Afghanistan, and examined whether awareness differed by demographic and professional factors. A quantitative descriptive survey design was employed, with data collected from 36 employees across 10 universities using a structured questionnaire distributed via Google Forms. Analysis in SPSS included descriptive statistics, the Kruskal–Wallis test, and the Mann–Whitney U test. Results indicated a moderate level of cybersecurity awareness overall. The highest mean score was reported for recognizing the importance of protecting sensitive data (M = 3.97, SD = 0.941), whereas the lowest was for effective communication of cybersecurity policies (M = 3.25, SD = 1.052). Inferential tests revealed no statistically significant differences in awareness across age (H(3) = 1.742, p = 0.628), education (H(2) = 0.399, p = 0.819), or work experience (H(3) = 4.826, p = 0.185). Similarly, no significant difference was observed between staff with and without prior cybersecurity training (U = 117.00, p = 0.379). These findings suggest that demographic and professional characteristics do not substantially influence cybersecurity awareness among the respondents. Universities should therefore prioritize strengthening institutional communication of cybersecurity policies and establishing continuous, structured awareness programs to enhance organizational cyber resilience and equip ICT staff to safeguard institutional data.
Development of a Website Based Cashier Application for Ayya Cell and Es Kristal Using the Research and Development (R&D) Method Jamaludin Jamaludin; Andri Nofiar.Am; Muhammad Arif
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 3 (2026): DECEMBER 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i3.8146

Abstract

The rapid development of digital technology has encouraged Micro, Small, and Medium Enterprises (MSMEs) to adopt information systems to improve operational efficiency and support business sustainability. However, many MSMEs, including AYYA Cell and Es Kristal, still rely on manual transaction recording, inventory management, and sales reporting, leading to operational inefficiencies and inaccurate business information. This study aims to develop a web-based Point of Sale (POS) application that integrates sales transactions, inventory management, customer management, and automated reporting within a single platform. The research employed the Research and Development (R&D) methodology consisting of six stages: needs analysis, system design, application development, system testing, implementation, and evaluation. The application was developed using the Laravel Framework and a MySQL database and evaluated through Black Box Testing and User Acceptance Testing (UAT) with ten respondents, including the business owner and employees. The functional testing results indicated that all system modules operated in accordance with the predefined requirements without critical errors. The UAT results achieved an average score of 4.62 out of 5.00, corresponding to a success rate of 92.4%, indicating a high level of user acceptance and usability. The findings demonstrate that the developed POS application effectively supports transaction processing, inventory control, reporting accuracy, and operational efficiency, contributing to the digital transformation of hybrid MSMEs by integrating digital service transactions and physical product sales into one unified web-based information system.
Analysis of the Paradigms and Effectiveness of Django Admin and Filament V4 in Rapid and Interactive Information System Development: A Case Study of the Borneo Link Material E-Commerce Application Praneta Dwi Indarti; Dinar Nugroho Pratomo
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 3 (2026): DECEMBER 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i3.8154

Abstract

Administrative panels are critical for e-commerce data governance, yet their implementation is often hindered by tight deadlines. Filament v4 and Django Admin provide rapid, model-driven back-office solutions, but direct empirical evaluations remain scarce. This study analyzes the architectural paradigms and operational effectiveness of Filament v4 and Django Admin using Rapid Application Development (RAD) on the Borneo Link e-commerce system, managing 1,000 material records under a two-month constraint without prior interface design. Both systems were constructed with equivalent schemas and validated through 35 black-box test cases across administrator and partner roles. The architectural evaluation demonstrates that Django Admin delivers superior simplicity and faster setup (2 minutes 4 seconds vs. 4 minutes 38 seconds), whereas Filament v4 provides greater modularity via dedicated resource and relation managers. Usability evaluations across ten representative respondents indicated that Filament v4 outperformed Django Admin in learnability (85.0% vs. 69.0%) and user engagement (84.5% vs. 60.5%), facilitated by built-in detail pages and input masking. Conversely, Django Admin exhibited higher operability (81.3% vs. 67.3%) and significantly faster response times across pagination, search, and filtering (529.2–613.8 ms vs. 901.28–1119.4 ms). These performance divergences stem from architectural differences between Django’s native server-side rendering and Filament’s Livewire-driven asynchronous request pipeline. These findings delineate an empirical trade-off between execution speed and interface interactivity, establishing actionable criteria for framework selection in rapid enterprise systems development.
Implementation of a Web-Based Smart Water Ordering System with Telegram Notification and Monitoring Dashboard for Olivia MSME Ropindo Pelix Pane; Mesra Betty Yel; Edhy Poerwandono
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 3 (2026): DECEMBER 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i3.8155

Abstract

Many micro, small, and medium enterprises (MSMEs) selling refillable drinking water still manage customer orders manually through phone calls and instant messaging, resulting in scattered transaction records, delayed responses, and limited operational monitoring. This study aimed to design, implement, and evaluate a web-based Smart Water Ordering System for Olivia MSME by integrating Quick Response Code Indonesian Standard (QRIS) payment, Telegram Bot notifications, and a centralized monitoring dashboard. The system was developed using the Waterfall Software Development Life Cycle (SDLC), encompassing requirement analysis, Unified Modeling Language (UML)-based system design, implementation using PHP and MySQL, and comprehensive system testing. The platform incorporates customer order placement, coordinate-based shipping-distance calculation, cashless transaction processing, and a moderated customer feedback mechanism. Functional validation through Black Box Testing confirmed that all core modules executed successfully without functional discrepancies, with the asynchronous Telegram webhook delivering order alerts in under two seconds. User Acceptance Testing involving 23 respondents (one administrator and twenty-two customers) yielded average satisfaction scores ranging from 4.7 to 4.9 out of 5, demonstrating high user acceptance across usability, interface clarity, feature suitability, information accessibility, and operational support. Practically, the system replaced conventional phone-based communication by centralizing transaction records, automating payment verification workflows, and providing real-time sales analytics through an integrated dashboard. These findings indicate that unifying transactional, payment, instant alert, and administrative monitoring components into a single web application effectively improves operational efficiency and accelerates the digital transformation of small-scale water-refill enterprises.
Developing an Indonesian Fake News Detection System Using IndoBERT and ProtoNet for Few-Shot Learning Yefta Christian; Wilson Wilson; Andik Yulianto
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 3 (2026): DECEMBER 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i3.8156

Abstract

Fake news dissemination through digital media has become a critical concern because inaccurate information may spread swiftly and influence public comprehension, social behavior, and decision-making. This study developed an Indonesian fake news detection web application employing fine-tuned IndoBERT and an IndoBERT-based Prototypical Network (ProtoNet) under few-shot learning scenarios. The research followed the Cross Industry Standard Process for Data Mining framework, consisting of business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The dataset was obtained from the publicly available Deteksi Berita Hoaks Indo Dataset on Kaggle and contained 23,944 Indonesian news records, consisting of 11,200 factual and 12,744 hoax articles. Three few-shot scenarios were evaluated: 50-shot, 100-shot, and 300-shot per class. IndoBERT was fine-tuned as a supervised classification baseline, while ProtoNet used IndoBERT embeddings to construct class prototypes and classify texts based on Euclidean distance. The best performance was achieved by fine-tuned IndoBERT in the 300-shot scenario, with 97.12% accuracy and a 97.10% macro F1-score. ProtoNet achieved 92.65% accuracy and a 92.63% macro F1-score in the same scenario. Even in the most constrained 50-shot setting, ProtoNet achieved an F1-score of 90.82%, closely trailing fine-tuned IndoBERT at 91.17% and demonstrating strong metric stability. The web application supports manual text input, URL-based article extraction, model selection, confidence scores, and word-level occlusion explanations. These results demonstrate the effectiveness of IndoBERT for Indonesian fake news detection and the feasibility of prototype-based classification under limited-data conditions. Overall, this work bridges the gap between deep contextual representation, data-efficient learning, and practical, interpretable deployment for public media verification.
Implementation of an IoT-Based Automatic Fish Seed Counting System Using NodeMCU ESP8266 with Telegram Notifications at Srikandi Fresh Fish MSME Putri Cahyani Sinaga; Rasiban Rasiban
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 3 (2026): DECEMBER 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i3.8206

Abstract

The counting of fish seeds at Srikandi Fresh Fish MSME is currently conducted through visual manual calculation, which is prone to human error, requires considerable operational time, and hinders accurate real-time inventory recording. To address these operational constraints, this research implemented an automated, Internet of Things (IoT)-based fish seed counting system using the NodeMCU ESP8266 microcontroller integrated with Google Sheets and a Telegram Bot service. The study utilized the Design Science Research (DSR) methodology, encompassing problem identification, objective definition, architectural design and development, artifact demonstration, functional evaluation, and communication. The developed hardware prototype incorporates an infrared sensor placed along a single-lane counting mechanism to detect individual passing fish seeds, an I2C-interfaced 16×2 liquid crystal display for local output, and NodeMCU ESP8266 as the core processing and communication unit. Telemetry data are logged automatically into Google Sheets via Google Apps Script and subsequently relayed to business operators as instant mobile notifications through a dedicated Telegram Bot after an inactivity period of 30 seconds. Functional validation using black-box testing confirmed that all hardware interfaces and software automated procedures operated as intended. Across 30 experimental trials involving varying seed densities, the counting mechanism achieved an average accuracy rate of 87.01% with an overall error margin of 12.99%, primarily attributed to occasional overlapping during high-density passages. The integrated cloud system also proved reliable during continuous operation, successfully reducing manual recording delays and providing an efficient, automated inventory monitoring solution for aquaculture small businesses.
Main Menu Sales Forecasting at Bakso Pak Eko MSME Using the Single Exponential Smoothing Method Gabriel Alezhandro Pakpahan; Mesra Betty Yel
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 3 (2026): DECEMBER 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i3.8215

Abstract

Sales volume is a critical factor influencing business sustainability, particularly for Micro, Small, and Medium Enterprises (MSMEs) operating in the perishable culinary sector. Bakso Pak Eko MSME faces persistent operational challenges in daily production planning, which currently relies on manual intuition and informal estimation, frequently resulting in inventory surpluses, ingredient spoilage, or unmet consumer demand. To address these operational inefficiencies, this study develops a responsive web-based sales forecasting system for primary menu items using the Single Exponential Smoothing (SES) method to support data-driven production scheduling. The SES method was selected due to its mathematical simplicity, low computational overhead, and proven efficacy in processing short-term historical sales records that exhibit stationary demand patterns without pronounced trend or seasonal fluctuations. The application was engineered using Python and the Streamlit framework, integrating dynamic menu catalog administration, daily transaction logging, customizable smoothing constants, automated forecasting routines, and real-time gross revenue estimation. Functional reliability was verified through Black Box Testing, while predictive performance was benchmarked using the Mean Absolute Percentage Error (MAPE) metric across three core menu items: regular meatballs, egg meatballs, and jumbo meatballs. The evaluation results demonstrate that the application operates reliably across all functional workflows without runtime anomalies. Configured with an optimal smoothing constant of α = 0.3, the model achieved a MAPE value of 1.56%, categorizing the forecast as highly accurate with an absolute deviation of only one to two portions per menu item. Furthermore, directly translating unit portion projections into daily revenue calculations provides the enterprise owner with actionable financial transparency alongside physical preparation targets. Consequently, this system effectively bridges computational modeling and shop-floor decision-making, enabling MSME managers to streamline raw material procurement, mitigate food waste, and enhance overall operational cost-efficiency.
Implementation of an AppSheet-Based Sales and Inventory Information System at Wijaya Baru Store Sri Lestari; Yara Raslita; Mesra Betty Yel
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 3 (2026): DECEMBER 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i3.8233

Abstract

Modern small and medium retail enterprises increasingly rely on digital information systems to streamline operational workflows and improve data accuracy. Toko Wijaya Baru previously conducted sales recording, inventory tracking, and financial reporting using conventional manual paper ledgers. This manual approach created substantial operational vulnerabilities, including calculation errors, delayed information retrieval, stock discrepancy risks, and potential data loss. This study aims to design, develop, and implement an integrated sales and inventory information system utilizing the AppSheet no-code platform to enhance operational efficiency, data reliability, and administrative accuracy. Data collection was conducted through qualitative observation, in-depth interviews, and document analysis, while the system development followed an iterative prototyping methodology to align functional modules with actual operational requirements. The system integrates an AppSheet user interface with Google Sheets as a cloud-based relational database backend, incorporating core features for master product management, sales transaction processing, restocking administration, automated real-time stock recalculation via dynamic formulas, and automated report generation. System validation through Black Box Testing demonstrated that all functional modules operate successfully without discrepancies. The post-implementation findings confirm that the system eliminates manual record redundancies, accelerates transaction throughput, prevents stock miscalculations, and provides structured sales visibility. Ultimately, this implementation demonstrates that an AppSheet-based no-code architecture serves as a practical, cost-effective, and scalable digital transformation solution for retail store management.
Implementation of a Progressive Web App for Teacher Attendance and Payroll System at PAUD Mckids West Bekasi Devara Isbani Yusuf; Veri Arinal; Mesra Betty Yel
International Journal Software Engineering and Computer Science (IJSECS) Vol. 6 No. 3 (2026): DECEMBER 2026
Publisher : Lembaga Komunitas Informasi Teknologi Aceh (KITA), Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/ijsecs.v6i3.8244

Abstract

PAUD McKids West Bekasi is an early childhood education institution that previously managed teacher attendance using manual paper logbooks and calculated payroll via basic spreadsheets. Consequently, the monthly recapitulation process required 2–3 working days and remained susceptible to human calculation errors. This study aims to design and implement a Progressive Web App (PWA) for the teacher attendance and payroll system, named SIPAG McKids, providing a computerized, integrated, and multi-device accessible administrative platform. The research employed the Research and Development (R&D) method using the Waterfall software engineering model, encompassing requirements analysis, system design, implementation, testing, and maintenance. The system was developed using the CodeIgniter 3 framework under the Model-View-Controller (MVC) architecture, a MySQL relational database, a Bootstrap 5 interface, DOMPDF for automated pay slip generation, and a Progressive Web App layer driven by a Web App Manifest and Service Workers to facilitate installation and offline caching. System evaluation comprised Black Box Testing for functional validation, PWA component verification, security assessments referencing the OWASP Top 10 guidelines, and performance audits using Google Lighthouse. The implementation results demonstrated that all Black Box testing scenarios functioned as designed. Security mechanisms—including Bcrypt password hashing, CSRF protection, Query Builder parameterization against SQL Injection, and Role-Based Access Control (RBAC)—operated correctly. Furthermore, self-service attendance based on selfie photography and GPS coordinates, alongside a tiered payroll approval workflow (Draft–Approved–Paid), operated successfully with transactional records verified in the production database. Google Lighthouse audit scores achieved 85 for desktop performance, 99 for mobile performance, 100 for Best Practices, 91 for SEO, and 78 for Accessibility. The system effectively enhances administrative recapitulation efficiency, improves calculation accuracy for tardiness deductions, ensures payroll transparency for teachers, and provides seamless mobile access for the institution.

Page 52 of 54 | Total Record : 535

 50   51   52   53   54 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol. 6 No. 3 (2026): DECEMBER 2026 Vol. 6 No. 2 (2026): AUGUST 2026 Vol. 6 No. 1 (2026): APRIL 2026 Vol. 5 No. 3 (2025): DECEMBER 2025 Vol. 5 No. 2 (2025): AUGUST 2025 Vol. 5 No. 1 (2025): APRIL 2025 Vol. 4 No. 3 (2024): DECEMBER 2024 Vol. 4 No. 2 (2024): AUGUST 2024 Vol. 4 No. 1 (2024): APRIL 2024 Vol. 3 No. 3 (2023): DECEMBER 2023 Vol. 3 No. 2 (2023): AUGUST 2023 Vol. 3 No. 1 (2023): APRIL 2023 Vol. 2 No. 2 (2022): OCTOBER 2022 Vol. 2 No. 1 (2022): MAY 2022 Vol. 1 No. 2 (2021): AUGUST 2021 Vol. 1 No. 1 (2021): APRIL 2021 More Issue