KLASIFIKASI JUDUL BERITA PALSU MENGGUNAKAN METODE BIDIRECTIONAL ENCODER REPRESENTATIONS FROM TRANSFORMERS (BERT)

ARKAN, MUHAMMAD ZIDANE and Yusliani, Novi and Marieska, Mastura Diana (2025) KLASIFIKASI JUDUL BERITA PALSU MENGGUNAKAN METODE BIDIRECTIONAL ENCODER REPRESENTATIONS FROM TRANSFORMERS (BERT). Undergraduate thesis, Sriwijaya University.

	Image RAMA_55201_09021182126014_COVER.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021182126014.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021182126014_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_55201_09021182126014_0008118205_0021038607_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021182126014_0008118205_0021038607_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (709kB) | Request a copy
	Text RAMA_55201_09021182126014_0008118205_0021038607_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (627kB) | Request a copy
	Text RAMA_55201_09021182126014_0008118205_0021038607_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021182126014_0008118205_0021038607_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021182126014_0008118205_0021038607_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (268kB) | Request a copy
	Text RAMA_55201_09021182126014_0008118205_0021038607_07_ref.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (315kB) | Request a copy
	Text RAMA_55201_09021182126014_0008118205_0021038607_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (181kB) | Request a copy

Abstract

This research aims to classify fake news headlines in Indonesian as an initial step in detecting and reducing the spread of misinformation. Headlines are often the first element read and have strong potential to shape public opinion, especially when they contain negative or sensational narratives. Unlike previous studies that analyze full news content or focus only on political news, this study uses the Bidirectional Encoder Representations from Transformers (BERT) approach to analyze news headlines. The dataset consists of 14,231 headlines from various categories, divided into training (6,972), validation (2,989), and test (4,270) sets. Experiments were conducted using nine scenarios that combine different parameters: epochs (10, 20, 30), learning rates (1e-4, 3e-5, 5e-5), and numbers of frozen BERT layers (6, 8, 10). Model performance was evaluated using a confusion matrix and metrics such as accuracy, precision, recall, and F1-score. The best result was achieved with 20 epochs, a learning rate of 3e-5, and 6 frozen layers, reaching an accuracy of 92.01%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Berita Palsu, Klasifikasi Berita, Pre-trained Model, BERT, Fine-Tuning, Akurasi
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Muhammad Zidane Arkan
Date Deposited:	14 May 2025 08:11
Last Modified:	14 May 2025 08:11
URI:	http://repository.unsri.ac.id/id/eprint/172360

Actions (login required)

View Item