ANALISIS SENTIMEN MEMBANDINGKAN ALGORITMA BLSTM DAN INDOBERT PADA KOMENTAR VIDEO CHARITY WINDAH BASUDARA

NURHAYAT, ABDUL IMAM (2025) ANALISIS SENTIMEN MEMBANDINGKAN ALGORITMA BLSTM DAN INDOBERT PADA KOMENTAR VIDEO CHARITY WINDAH BASUDARA. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 COVER.pdf Download (515kB) | Preview
	Text (BAB I) 02 BAB 1.pdf Restricted to Registered users only Download (107kB)
	Text (BAB II) 03 BAB 2.pdf Restricted to Registered users only Download (369kB)
	Text (BAB III) 04 BAB 3.pdf Restricted to Registered users only Download (299kB)
	Text (BAB IV) 05 BAB 4.pdf Restricted to Registered users only Download (279kB)
	Text (BAB V) 06 BAB 5.pdf Restricted to Registered users only Download (122kB)
	Text (DAFTAR PUSTAKA) 07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (160kB)
	Text (LAMPIRAN) 08 LAMPIRAN.pdf Restricted to Registered users only Download (1MB)

Abstract

Sentiment analysis is a crucial area within Natural Language Processing (NLP) used to understand opinions or emotions expressed in text. This study aims to evaluate and compare the performance of two sentiment analysis algorithms— BLSTM (Bidirectional Long Short-Term Memory) and IndoBERT—in classifying sentiments from YouTube comments, specifically on a charity video uploaded by Windah Basudara. These comments are typically written in informal Indonesian, often containing slang, abbreviations, and expressions commonly used by internet users. The research involves text preprocessing, sentiment labeling, model training, and performance evaluation using accuracy, precision, recall, and F1-score metrics. The results show that the IndoBERT algorithm outperforms BLSTM in handling informal Indonesian texts. Therefore, this study is expected to contribute to the development of more accurate and adaptive sentiment analysis models for social media content in the Indonesian language. Keywords: Sentiment Analysis, BLSTM, IndoBERT, YouTube Comments, Windah Basudara, Informal Indonesian Language. Analisis sentimen merupakan salah satu bidang penting dalam pemrosesan bahasa alami (Natural Language Processing/NLP) yang digunakan untuk memahami opini atau emosi dalam teks. Penelitian ini bertujuan untuk mengevaluasi dan membandingkan kinerja dua algoritma analisis sentimen, yaitu BLSTM (Bidirectional Long Short-Term Memory) dan IndoBERT, dalam mengklasifikasikan sentimen pada komentar video YouTube, khususnya pada video charity yang diunggah oleh Windah Basudara. Komentar-komentar tersebut umumnya ditulis dalam bahasa Indonesia informal yang mengandung bahasa gaul, singkatan, dan ekspresi khas warganet. Penelitian dilakukan melalui tahapan preprocessing teks, pelabelan sentimen, pelatihan model, serta evaluasi performa menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa algoritma IndoBERT memberikan performa yang lebih baik dibandingkan BLSTM dalam menangani teks informal berbahasa Indonesia. Dengan demikian, penelitian ini diharapkan dapat memberikan kontribusi terhadap pengembangan model analisis sentimen yang lebih akurat dan adaptif untuk konteks sosial media di Indonesia. Kata kunci: Analisis Sentimen, BLSTM, IndoBERT, Komentar YouTube, Windah Basudara, Bahasa Indonesia Informal.

Item Type:	Thesis (S1)
Call Number CD:	FIK/INFO. 25 114
NIM/NIDN Creators:	41521010180
Uncontrolled Keywords:	Analisis Sentimen, BLSTM, IndoBERT, Komentar YouTube, Windah Basudara, Bahasa Indonesia Informal.
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 > 006.6 Computer Graphics/Komputer Grafis, Grafika Komputer 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 500 Natural Science and Mathematics/Ilmu-ilmu Alam dan Matematika > 510 Mathematics/Matematika > 518 Numerical Analysis/Analisis Numerik, Analisa Numerik > 518.1 Algorithms/Algoritma 700 Arts/Seni, Seni Rupa, Kesenian > 770 Photography and Photographs/Seni Fotografi dan Foto > 778 Specific Fields of Photography/Bidang-bidang Khusus Seni Fotografi > 778.5 Cinematography, Video Production, Related Activities/Sinematografi, Produksi Video, dan Kegiatan Terkait > 778.52 General Topics of Cinematography and Video Production/Topik-topik Umum Mengenai Sinematografi dan Produksi Video
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	khalimah
Date Deposited:	05 Aug 2025 02:56
Last Modified:	05 Aug 2025 02:56
URI:	http://repository.mercubuana.ac.id/id/eprint/96561

Actions (login required)

View Item