Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Niluh Putu Vania Dyah Saraswati
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Analisis Sentimen terhadap Perundungan Siber pada Twitter menggunakan Algoritma Bidirectional Encoder Representations from Transformer (BERT) Niluh Putu Vania Dyah Saraswati; Novanto Yudistira; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 2 (2023): Februari 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Bullying is the deliberate act of hurting physically, verbally, and psychologically someone who feels helpless. Bullying is an important issue that has been / is identified as a very serious social problem in the United States and many other parts of the world. Cyberbullying is the use of information and communication technologies for intentional/planned harassment and hostile activities, which are carried out repeatedly and structured in a potentially harmful manner. Types of cyberbullying include bullying someone through social media, harassment, sexting, fraud, impersonating, and sending malicious messages through chat rooms and instant messaging. Over the past few years, Bidirectional Encoder Representation from Transformers (BERT) has become a widely used and efficient representation model that achieves cutting-edge performance on sentence-level and token-level tasks, outperforming many specialized task architectures. The level of accuracy in the classification of cyberbullying using test data and validation data in Indonesian generated using the Bert algorithm is 0.81 which in percentage accuracy is 81%. BERT's algorithm can help identify inputs that lead to cyberbullying by providing outputs in the form of classes with predefined categories, namely neutral, abusive language or containing hate speech. The system also gives a percentage of the categories obtained through the program.
Co-Authors Novanto Yudistira Putra Pandu Adikara