Jurnal Ilmu Siber dan Teknologi Digital

WEB-BASED RESEARCH ARTICLE CLASSIFICATION USING THE RANDOM FOREST ALGORITHM

2025-09-25T11:51:48+07:00

Purpose: This study aims to develop a web-based system that classifies research articles using the Random Forest algorithm to address mismatches between article content and journal scope.

Methodology/approach: The research employed the SDLC Waterfall model, with data sourced from 560 articles published by Goodwood Publishing (2019–2024) across four categories. Text preprocessing included case folding, stopword removal, stemming, and tokenization, with TF-IDF applied for feature extraction. Random Forest was trained with 80% training data and 20% testing data.

Results/findings: The model achieved 91% accuracy, with high precision and recall across all categories. The system was successfully implemented as a web-based application, providing instant classification and journal recommendations.

Limitations: The dataset was limited to one publisher and only Random Forest was applied, which may restrict the generalizability of findings.

Contribution: This study contributes to the application of machine learning in scholarly publishing, offering a practical solution for editors to streamline article selection and improve efficiency.

Android Based Rosella Tea Sales Application as Digital Innovation

2025-12-11T15:01:20+07:00

Purpose: This study aims to develop an Android-based sales application for Rosella Tea as a digital innovation, addressing the need for efficient marketing and sales management among Women Farmers Groups (KWT) in East Ambarawa Village, Lampung.

Methodology/approach: The research utilizes the System Development Life Cycle (SDLC) method, with stages including needs analysis, system design using Unified Modeling Language (UML), coding with Java, and data storage via Firebase.

Results/findings: The developed application successfully operates on Android devices, presenting products informatively and enabling real-time transactions and sales management. It enhances marketing efficiency and expands the market reach for Rosella Tea, improving transaction processes between sellers and buyers.

Conlusion: The Android-based application serves as an innovative solution to promote Rosella Tea digitally, offering better sales management, expanding market access, and increasing business efficiency for women farmers.

Limitations: The study did not explore the full range of features needed, such as integration with various payment methods and e-commerce platforms.

Contribution: The application provides a digital pathway for Women Farmers Groups to manage and promote local products, contributing to their economic empowerment and aligning with government initiatives to support MSMEs' digitalization.

UML-Based Design of a GIS-Based E-Commerce Application for MSMEs

2026-02-12T15:01:20+07:00

Purpose: This study aims to design a Geographic Information System (GIS)-based e-commerce application for Micro, Small, And Medium Enterprises (MSMEs) using the Unified Modeling Language (UML). The novelty of this study lies in the integration of UML modeling with GIS-based features to support spatial visualization in MSME e-commerce systems, which is limited in prior studies.

Methodology/approach: This research adopts a Research and Development (R&D) approach using the waterfall model, which was selected because of its suitability for structured system design with clearly defined requirements.

Results/Findings: The results demonstrate that UML modeling, including use case, activity, and class diagrams, successfully represents system functionality, user interactions, and data structures in a systematic and consistent manner. The completeness and consistency of the model were evaluated based on the alignment between system requirements and diagram representation. However, this study is limited to system design without full implementation and empirical testing.

Conclusions: This study introduces a GIS-based e-commerce design for MSMEs using UML modelling, a novel approach in integrating spatial features. The UML models effectively represent system functions and data. However, the study is limited by the lack of implementation and testing. Future research should focus on full implementation and empirical validation.

Limitations: This study has limitations in that comprehensive system implementation and testing have not been conducted.

Contributions: This research contributes conceptually and methodologically by providing a structured UML-based design model for GIS-integrated MSME e-commerce systems that can be used as a reference for future development and implementation.