IMPLEMENTASI SENTIMEN ANALISIS PADA TWITTER MENGGUNAKAN BERT TERHADAP KOMENTAR KENAIKAN HARGA BEBERAPA KOMODITAS DALAM DUA BAHASA

FARHAN, MUHAMMAD (2024) IMPLEMENTASI SENTIMEN ANALISIS PADA TWITTER MENGGUNAKAN BERT TERHADAP KOMENTAR KENAIKAN HARGA BEBERAPA KOMODITAS DALAM DUA BAHASA. S1 thesis, Universitas Mercu Buana Jakarta.

	Text (HAL COVER) 01 Cover.pdf Download (388kB)
	Text (ABSTRAK) 02 Abstrak.pdf Download (32kB)
	Text (BAB I) 03 Bab 1.pdf Restricted to Registered users only Download (45kB)
	Text (BAB II) 04 Bab 2.pdf Restricted to Registered users only Download (361kB)
	Text (BAB III) 05 Bab 3.pdf Restricted to Registered users only Download (202kB)
	Text (BAB IV) 06 Bab 4.pdf Restricted to Registered users only Download (470kB)
	Text (BAB V) 07 Bab 5.pdf Restricted to Registered users only Download (27kB)
	Text (DAFTAR PUSTAKA) 08 Daftar Pustaka.pdf Restricted to Registered users only Download (130kB)
	Text (LAMPIRAN) 09 Lampiran.pdf Restricted to Registered users only Download (1MB)

Abstract

Twitter is a leading social media platform with over 1 billion users on Google PlayStore. This is a place to share feedback, data and connect. Here we often discuss increases in the prices of raw materials such as fuel, basic materials and others. Food availability is very important and this research uses a new approach, namely the BERT model, to analyze sentiment on Twitter. We tested BERT pre-training models, specifically mBERT, on Tweet comments about price increases. We found that the optimized Indonesian mBERT model had great accuracy (95%) with some hyperparameters. The data labeling procedure influences the results, with TextBlob-based Indonesian labeling providing the highest accuracy. The mBERT model can predict sentiment well and the best results are achieved with 95% accuracy on Indonesian language data using hyperparameters, i.e. learning rate 0.00002, batch size 32, number of epochs 5 and training time 10 minutes. Keywords: Sentiment Analysis, BERT, Twitter, NLP Twitter merupakan platform media sosial terkemuka dengan lebih dari 1 miliyar pengguna di Google PlayStore. Ini merupakan tempat buat berbagi komentar, data, serta berhubungan. Peningkatan harga komoditas semacam bahan bakar, bahan pokok, serta yang lain kerap dibahas di sini. Ketersediaan pangan sangat berarti, serta riset ini memanfaatkan pendekatan baru ialah model BERT guna menganalisis sentimen di Twitter. Kami menguji model pre- training BERT, khususnya mBERT, pada komentar Tweet tentang peningkatan harga. Kami mendeteksi kalau model fine- tuned mBERT bahasa Indonesia mempunyai akurasi besar( 95%) dengan hyperparameter tertentu. Tata cara pelabelan data mempengaruhi hasil, dengan pelabelan berbasis TextBlob bahasa Indonesia memberikan akurasi terbaik. Model mBERT dapat memprediksi sentimen dengan baik, serta hasil terbaik diperoleh dengan akurasi 95% pada data bahasa Indonesia memakai hyperparameter yaitu Learning Rate 0.00002, Batch Size 32, jumlah Epoch 5 dan waktu pelatihan 10 menit. Kata kunci: Analisis sentimen, BERT, Twitter, NLP

Item Type:	Thesis (S1)
Call Number CD:	FIK/INFO. 24 052
Call Number:	SIK/15/24/045
NIM/NIDN Creators:	41518110084
Uncontrolled Keywords:	Analisis sentimen, BERT, Twitter, NLP
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 > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika 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 > 006 Special Computer Methods/Metode Komputer Tertentu > 006.7 Multimedia Systems/Sistem-sistem Multimedia > 006.75 Social Multimedia/Multimedia Social 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 > 006 Special Computer Methods/Metode Komputer Tertentu > 006.7 Multimedia Systems/Sistem-sistem Multimedia > 006.75 Social Multimedia/Multimedia Social > 006.754 Online Social Network/Situs Jejaring Sosial, Sosial Media 100 Philosophy and Psychology/Filsafat dan Psikologi > 150 Psychology/Psikologi > 154 Subconscious and Altered States and Process/Psikologi Bawah Sadar > 154.6 Sleep Phenomena/Fenomena Tidur > 154.63 Dreams/Mimpi > 154.634 Analysis/Analisis
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	khalimah
Date Deposited:	27 Feb 2024 04:27
Last Modified:	27 Feb 2024 04:27
URI:	http://repository.mercubuana.ac.id/id/eprint/86583

Actions (login required)

View Item