Garuda - Garba Rujukan Digital

Boosting Methods for Multi-label Data Cyberbullying Farasalsabila, Fidya; Aritonang, Mhd Adi Setiawan; Jabnabillah, Faradiba; Moniva, Anip; Lestari, Verra Budhi; Handayani, Rizky
JURIKOM (Jurnal Riset Komputer) Vol 12, No 3 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i3.8721

Easy accessibility to the internet and social media allows individuals to communicate anonymously, providing opportunities for abusive and harmful behavior. The psychological impact of cyberbullying can be very detrimental, triggering stress, depression, and even causing more serious consequences such as suicide. This paper describes cyberbullying sentiment analysis with a focus on the use of four different boosting methods, namely Gradient Booster, Gradient Booster, XGBoost, AdaBoost, dan LightGBM on a multi-label public dataset covering 6 categories. The aim of this research is to compare and analyze the relative performance of these boosting methods in overcoming the challenges of multi-label sentiment analysis in the context of cyberbullying. Results reveal that XGBoost and LightGBM have a tendency to more effectively overcome the challenges of detecting cyberbullying in more complex categories, making a positive contribution to the development of superior detection systems in the context of multi-label sentiment analysis. This research contributes to the field by providing a comparative analysis of state-of-the-art boosting algorithms, highlighting their strengths in multi-label classification tasks, and offering practical insights for developing more accurate and reliable cyberbullying detection systems. The findings from this study are expected to serve as a reference for future development of machine learning-based tools that can help mitigate the psychological harm caused by online abuse, particularly in detecting subtle and complex forms of cyberbullying behavior.

Development of Sustainable Curriculum Management System with Server-Driven Go and Next.js Fitrianto, Adi; Kangadi, Farel Artanto; Rizki, Sestri Novia; Lestari, Verra Budhi; Jaya, Eko Amri
Brilliance: Research of Artificial Intelligence Vol. 5 No. 2 (2025): Brilliance: Research of Artificial Intelligence, Article Research November 2025
Publisher : Yayasan Cita Cendekiawan Al Khwarizmi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/brilliance.v5i2.5381

Curriculum management is a crucial aspect of educational administration, encompassing the planning, organization, and continuous updating of course data and curriculum structures. In many educational institutions, including those in Jakarta, this process still encounters challenges such as inefficiency, data duplication, inconsistent information flow, and high system maintenance overhead. These issues often result in delays, administrative burdens, and reduced productivity. This research aims to develop a sustainable curriculum management system by leveraging Go technology on the backend and Next.js on the frontend, adopting a server-driven approach to minimize processing loads on client devices, improve resource efficiency, and ensure faster data delivery. The system development method employs an iterative approach with the integration of ten supporting technologies, including server-side data fetching, Backend for Frontend (BFF), OpenAPI 3 with code generation, Redis caching, tag-based revalidation, Server-Sent Events (SSE), component-based UI, image optimization, and asynchronous job queues for heavy tasks. The system integrates course and curriculum name management into a single, responsive, secure, and easily extensible platform. Implementation results demonstrate that the approach can reduce maintenance complexity, improve data consistency, and significantly enhance application response time under varying loads. Furthermore, the system supports sustainable software engineering principles, enabling scalability and adaptability to future needs. Consequently, it offers an effective, long-term solution for curriculum management, contributing to operational efficiency and the overall quality of academic administration in educational institutions across Jakarta.

Boosting Methods for Multi-label Data Cyberbullying Farasalsabila, Fidya; Aritonang, Mhd Adi Setiawan; Jabnabillah, Faradiba; Moniva, Anip; Lestari, Verra Budhi; Handayani, Rizky
JURNAL RISET KOMPUTER (JURIKOM) Vol. 12 No. 3 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i3.8721

Easy accessibility to the internet and social media allows individuals to communicate anonymously, providing opportunities for abusive and harmful behavior. The psychological impact of cyberbullying can be very detrimental, triggering stress, depression, and even causing more serious consequences such as suicide. This paper describes cyberbullying sentiment analysis with a focus on the use of four different boosting methods, namely Gradient Booster, Gradient Booster, XGBoost, AdaBoost, dan LightGBM on a multi-label public dataset covering 6 categories. The aim of this research is to compare and analyze the relative performance of these boosting methods in overcoming the challenges of multi-label sentiment analysis in the context of cyberbullying. Results reveal that XGBoost and LightGBM have a tendency to more effectively overcome the challenges of detecting cyberbullying in more complex categories, making a positive contribution to the development of superior detection systems in the context of multi-label sentiment analysis. This research contributes to the field by providing a comparative analysis of state-of-the-art boosting algorithms, highlighting their strengths in multi-label classification tasks, and offering practical insights for developing more accurate and reliable cyberbullying detection systems. The findings from this study are expected to serve as a reference for future development of machine learning-based tools that can help mitigate the psychological harm caused by online abuse, particularly in detecting subtle and complex forms of cyberbullying behavior.

APPLYING USER-CENTERED DESIGN FOR MOBILE APPLICATIONS INTERFACE DESIGN Farasalsabila, Fidya; Lestari, Verra Budhi; Nugroho, Jangkung Tri; Pramudyantoro, Arvi; Utami, Ema
JURTEKSI (jurnal Teknologi dan Sistem Informasi) Vol. 10 No. 1 (2023): Desember 2023
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Royal Kisaran

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurteksi.v10i1.2619

Abstract: The Healthy Food Supplier App, which introduces groundbreaking innovations to increase public access to and delivery of healthy food, has emerged as a new phenomenon in the food sector. This research intends to examine and describe how the use of healthy food suppliers contributes to improving public health by making healthy food accessible to obtain and deliver it quickly. The development of mobile applications with the aim of providing healthy food and ingredients for the community is the subject of this research. The aim of this app is to provide original responses to issues related to raising awareness of quality of life and the value of nutritious food in everyday life. The User Centered Design (UCD) method needs to be applied to categorize various user information needs and package them into a mobile application design model. The results of the application design showed that the interface design for the pioneer food and health food raw material application was successfully created using the implementation of the UCD method with a number of revisions that have been updated since the evaluation as one of the feature developments in the application. The food recording feature and personalized recommendations implemented in this mobile application provide users with awareness and guidance in adopting healthier eating patterns. Keywords: Design Interface; Mobile Applications; Requirements Engineering; User-Centered Design Abstrak: Aplikasi Pemasok Makanan Sehat yang memperkenalkan inovasi terobosan untuk meningkatkan akses publik ke dan pengiriman makanan sehat, telah muncul sebagai fenomena baru di sektor makanan. Penelitian ini bermaksud untuk mengkaji dan mendeskripsikan bagaimana penggunaan pemasok makanan sehat berkontribusi dalam peningkatan kesehatan masyarakat dengan membuat makanan sehat dapat diakses untuk mendapatkan dan mengantarkannya dengan cepat. Pengembangan aplikasi mobile dengan tujuan menyediakan makanan dan bahan makanan sehat bagi masyarakat menjadi pokok bahasan penelitian ini. Tujuan dari aplikasi ini adalah untuk memberikan tanggapan orisinal terhadap masalah yang terkait dengan peningkatan kesadaran kualitas hidup dan nilai makanan bergizi dalam kehidupan sehari-hari. Metode User Centered Design (UCD) perlu diterapkan untuk mengkategorikan berbagai kebutuhan informasi pengguna dan mengemasnya ke dalam model desain aplikasi mobile. Hasil perancangan aplikasi didapatkan bahwa desain antarmuka aplikasi pelopor makanan dan bahan baku makanan kesehatan berhasil dibuat dengan menggunakan implementasi metode UCD dengan sejumlah revisi yang sudah diperbarui sejak evaluasi sebagai salah satu pengembangan fitur pada aplikasi. Fitur pencatatan makanan dan rekomendasi personal yang diterapkan pada aplikasi mobile ini memberikan pengguna kesadaran dan panduan dalam mengadopsi pola makan yang lebih sehat. Kata Kunci: Design Interface; Mobile Applications; Requirements Engineering; User-Centered Design

Title

Found 4 Documents
Search

Abstract

Abstract

Abstract

Abstract

Title Search

Found 4 Documents Search

Abstract

Abstract

Abstract

Abstract

Title

Found 4 Documents
Search