DETEKSI BERITA HOAX BERBAHASA INDONESIA MENGGUNAKAN ALGORITMA BERT DAN LSTM

FAHMI, DZUL (2023) DETEKSI BERITA HOAX BERBAHASA INDONESIA MENGGUNAKAN ALGORITMA BERT DAN LSTM. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 Cover.pdf Download (394kB) | Preview
Preview	Text (ABSTRAK) 02 Abstrak.pdf Download (29kB) | Preview
	Text (BAB I) 03 Bab 1.pdf Restricted to Registered users only Download (87kB)
	Text (BAB II) 04 Bab 2.pdf Restricted to Registered users only Download (223kB)
	Text (BAB III) 05 Bab 3.pdf Restricted to Registered users only Download (144kB)
	Text (BAB IV) 06 Bab 4.pdf Restricted to Registered users only Download (414kB)
	Text (BAB V) 07 Bab 5.pdf Restricted to Registered users only Download (24kB)
Preview	Text (DAFTAR PUSTAKA) 09 Daftar Pustaka.pdf Download (89kB) | Preview
	Text (LAMPIRAN) 10 Lampiran.pdf Restricted to Registered users only Download (539kB)

Abstract

Today, Information and Communication Technology (ICT) is developing very rapidly. Various media, one of which is social media, is a forum for disseminating information that is very influential in people's lives. The dissemination of information or news through social media is currently not only carried out by trusted news sites but also by all internet users. But unfortunately a lot of information or what is spread on social media cannot be justified for its truth or is called a hoax. This study aims to create a hoax news detection system which will later be classified by the Bidirectional Encoder Representations from Transformers (BERT) Algorithm and Long Short-Term Memory (LSTM), then the results of the classification are 2 classes, namely negative and positive classes. The research method used is data collection, data cleaning and classification. The results of the performance analysis using the BERT algorithm get the best results with an accuracy rate of 84%, 74% precision, 72% recall, and 73% f1-score. While the LSTM algorithm gets the best results with an accuracy rate of 83%, 71% precision, 67% recall and 68% f1-score. Key words: hoax news, BERT, LSTM Dewasa ini, Teknologi Informasi dan Komunikasi (TIK) berkembang sangat pesat. Beragam media salah satunya media sosial menjadi salah satu wadah penyebaran informasi yang sangat berpengaruh kepada kehidupan masyarakat. Penyebaran informasi atau berita melalui media sosial saat ini tidak hanya dilakukan oleh situs berita terpercaya namun juga oleh semua pengguna internet. Namun sayangnya banyak informasi atau yang disebarkan di media sosial tidak dapat dipertanggungjawabkan kebenerannya atau disebut dengan hoax. Penelitian ini bertujuan untuk membuat suatu sistem deteksi berita hoax yang nantinya diklasifikasikan oleh Algoritma Bidirectional Encoder Representations from Transformers (BERT) dan Long Short-Term Memory (LSTM), kemudian hasil klasifikasi tersebut terdapat 2 kelas yaitu kelas negatif dan positif. Metode penelitian yang digunakan yaitu pengumpulan data, pembersihan data dan klasifikasi. Hasil performa analisis menggunakan algoritma BERT mendapatkan hasil terbaik dengan tingkat akurasi 84%, presisi 74%, recall 72%, dan f1-score 73%. Sedangkan algoritma LSTM mendapatkan hasil terbaik dengan tingkat akurasi 83%, presisi 71%, recall 67% dan f1-score 68%. Kata kunci: berita hoax, BERT, LSTM

Item Type:	Thesis (S1)
Call Number CD:	FIK/INFO. 23 045
Call Number:	SIK/15/23/041
NIM/NIDN Creators:	41519120136
Uncontrolled Keywords:	berita hoax, BERT, LSTM
Subjects:	000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika 600 Technology/Teknologi > 610 Medical, Medicine, and Health Sciences/Ilmu Kedokteran, Ilmu Pengobatan dan Ilmu Kesehatan > 617 Surgery, Regional Medicine, Dentistry, Ophthalmology, Otology, Audiology/Pembedahan, Kedokteran Daerah, Kedokteran Gigi, Oftalmologi, Otologi, Audiologi > 617.9 Auxiliary Techniques and Procedures, Apparatus and Equipment of Surgical Appliances/Teknik, Prosedur, Alat-alat dan Perlengkapan Pembedahan
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	MILA RISKA
Date Deposited:	13 May 2023 03:53
Last Modified:	15 May 2023 05:29
URI:	http://repository.mercubuana.ac.id/id/eprint/75842

Actions (login required)

View Item