Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab Jurnal Mantik Penusa
Hendra Pasaribu
Universitas Prima Indonesia
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
PERANCANGAN APLIKASI HASHING FILE MENGGUNAKAN SHA – 224 BERBASIS ANDROID Hendra Pasaribu; Muhammad Fauzi Harahap
Jurnal Mantik Penusa Vol. 4 No. 1 (2020): Management and Informatics
Publisher : Lembaga Penelitian dan Pengabdian (LPPM) STMIK Pelita Nusantara Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Nowadays the development of technology in the field of computer science is growing rapidly. With the rapid development of technology in the field of computer science, information and data require a security and confidentiality because the information becomes a very valuable item. However, with the development of technology there are also many threats of crime against files that users have. One way to maintain the authenticity of information and data is to use hash cryptography. The hash function is an algorithm that converts text / messages into a series of random characters that have the same number of characters. The hash function is used to guarantee the authentication service of messages or files. Algorithms that use hash functions include MD5, SHA-1, SHA-2 (SHA - 224, SHA - 256, SHA - 384, SHA - 512) and others that have their advantages and disadvantages. In designing this application, the cryptographic algorithm used is the SHA-224 algorithm, because SHA-224 has a summary of variable sizes. The file hashing application using the Android-based SHA-224 algorithm, can help users to maintain the authenticity of files from users anywhere and anytime. Users can also compare the authenticity of user files with files that have been hashed.
PEMANFAATAN MACHINE LEARNING MODEL INDOBERT UNTUK MENGIDENTIFIKASI CYBERBULLYING PADA KOLOM KOMENTAR SOSIAL MEDIA YOUTUBE: artikel Hendra Pasaribu; Daniel Septian Feri Bancin; Dian Karina Sembiring; Joyakim Simarmata; Vrendy Gusman Gulo
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8092

Abstract

The growth of social media, particularly YouTube, has led to increased user interaction through comment sections. The high volume of comments has also given rise to various forms of negative content, such as insults, harassment, sarcasm, and verbal attacks, which can be categorized as Cyberbullying. Therefore, an automated system capable of identifying Cyberbullying comments is needed. This study aims to develop a Cyberbullying detection system for Indonesian-language YouTube comments using the IndoBERT model. The dataset was collected through a YouTube comment scraping process using the YouTube Data API from Indonesian content videos published between 2019 and 2024. The research stages included data preprocessing, manual labeling, dataset balancing, tokenization, model training, model evaluation, and the implementation of a web-based system using Laravel and FastAPI. The final dataset consisted of 9,298 comments categorized into Cyberbullying, Non-Bullying, and Undifine/Invalid Data classes. The training process utilized the indobenchmark/indobert-base-p1 model with an 80:20 split between training and testing data. Based on the evaluation results, the model achieved an accuracy of 81.45%, precision of 85.49%, recall of 79.64%, F1-score of 81.87%, and an AUC score of 93.90%. These results indicate that the IndoBERT model is capable of effectively classifying Cyberbullying comments in Indonesian-language YouTube comments. Furthermore, the developed system can assist in the automatic identification of Cyberbullying comments and demonstrates that the IndoBERT model is effective for analyzing Indonesian-language social media text.
Co-Authors Daniel Septian Feri Bancin Dian Karina Sembiring Joyakim Simarmata Muhammad Fauzi Harahap Vrendy Gusman Gulo