Sentiment Analysis of Emoji and Latinized Arabic in Indonesian Youtube Comments: A LABERT-LSTM Model

This study addresses the challenges of sentiment analysis on Indonesian-language YouTube comments, which are complex due to the use of dialects, slang words, emojis, and Latinized Arabic text. The proposed LABERT-LSTM model integrates BERT for deep feature extraction and Bi-LSTM to capture word seq...

Full description

Saved in:
Bibliographic Details
Main Authors: M. Noer Fadli Hidayat, Didik Dwi Prasetya, Triyanna Widiyaningtyas
Format: Article
Language:English
Published: Yayasan Pendidikan Riset dan Pengembangan Intelektual (YRPI) 2025-06-01
Series:Journal of Applied Engineering and Technological Science
Subjects:
Online Access:http://journal.yrpipku.com/index.php/jaets/article/view/7000
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849724594012815360
author M. Noer Fadli Hidayat
Didik Dwi Prasetya
Triyanna Widiyaningtyas
author_facet M. Noer Fadli Hidayat
Didik Dwi Prasetya
Triyanna Widiyaningtyas
author_sort M. Noer Fadli Hidayat
collection DOAJ
description This study addresses the challenges of sentiment analysis on Indonesian-language YouTube comments, which are complex due to the use of dialects, slang words, emojis, and Latinized Arabic text. The proposed LABERT-LSTM model integrates BERT for deep feature extraction and Bi-LSTM to capture word sequence context effectively. The dataset comprises 24,593 YouTube comments from five renowned Islamic preachers discussing the topic of “tahlilan”. After data preprocessing, the model was evaluated using accuracy, precision, recall, and F1-score metrics. The results demonstrate that LABERT-LSTM achieved an accuracy of 0.95756, precision of 0.94014, recall of 0.91815, and an F1-score of 0.92868, outperforming standalone BERT and Bi-LSTM models by reducing misclassification and improving predictions for negative, positive, and neutral sentiment classes. Future research recommendations include expanding the dataset to other social media platforms, adopting advanced NLP techniques, conducting studies in other languages, and optimizing the model for enhanced performance and computational efficiency.
format Article
id doaj-art-ca1e50dce8c848feb520f9bff13762a2
institution DOAJ
issn 2715-6087
2715-6079
language English
publishDate 2025-06-01
publisher Yayasan Pendidikan Riset dan Pengembangan Intelektual (YRPI)
record_format Article
series Journal of Applied Engineering and Technological Science
spelling doaj-art-ca1e50dce8c848feb520f9bff13762a22025-08-20T03:10:41ZengYayasan Pendidikan Riset dan Pengembangan Intelektual (YRPI)Journal of Applied Engineering and Technological Science2715-60872715-60792025-06-016210.37385/jaets.v6i2.7000Sentiment Analysis of Emoji and Latinized Arabic in Indonesian Youtube Comments: A LABERT-LSTM Model M. Noer Fadli Hidayat0Didik Dwi Prasetya1Triyanna Widiyaningtyas2Universitas Negeri MalangUniversitas Negeri MalangUniversitas Negeri Malang This study addresses the challenges of sentiment analysis on Indonesian-language YouTube comments, which are complex due to the use of dialects, slang words, emojis, and Latinized Arabic text. The proposed LABERT-LSTM model integrates BERT for deep feature extraction and Bi-LSTM to capture word sequence context effectively. The dataset comprises 24,593 YouTube comments from five renowned Islamic preachers discussing the topic of “tahlilan”. After data preprocessing, the model was evaluated using accuracy, precision, recall, and F1-score metrics. The results demonstrate that LABERT-LSTM achieved an accuracy of 0.95756, precision of 0.94014, recall of 0.91815, and an F1-score of 0.92868, outperforming standalone BERT and Bi-LSTM models by reducing misclassification and improving predictions for negative, positive, and neutral sentiment classes. Future research recommendations include expanding the dataset to other social media platforms, adopting advanced NLP techniques, conducting studies in other languages, and optimizing the model for enhanced performance and computational efficiency. http://journal.yrpipku.com/index.php/jaets/article/view/7000Analisis SentimenLatinized ArabicEmojiBERTBi-LSTMLABERT-LSTM
spellingShingle M. Noer Fadli Hidayat
Didik Dwi Prasetya
Triyanna Widiyaningtyas
Sentiment Analysis of Emoji and Latinized Arabic in Indonesian Youtube Comments: A LABERT-LSTM Model
Journal of Applied Engineering and Technological Science
Analisis Sentimen
Latinized Arabic
Emoji
BERT
Bi-LSTM
LABERT-LSTM
title Sentiment Analysis of Emoji and Latinized Arabic in Indonesian Youtube Comments: A LABERT-LSTM Model
title_full Sentiment Analysis of Emoji and Latinized Arabic in Indonesian Youtube Comments: A LABERT-LSTM Model
title_fullStr Sentiment Analysis of Emoji and Latinized Arabic in Indonesian Youtube Comments: A LABERT-LSTM Model
title_full_unstemmed Sentiment Analysis of Emoji and Latinized Arabic in Indonesian Youtube Comments: A LABERT-LSTM Model
title_short Sentiment Analysis of Emoji and Latinized Arabic in Indonesian Youtube Comments: A LABERT-LSTM Model
title_sort sentiment analysis of emoji and latinized arabic in indonesian youtube comments a labert lstm model
topic Analisis Sentimen
Latinized Arabic
Emoji
BERT
Bi-LSTM
LABERT-LSTM
url http://journal.yrpipku.com/index.php/jaets/article/view/7000
work_keys_str_mv AT mnoerfadlihidayat sentimentanalysisofemojiandlatinizedarabicinindonesianyoutubecommentsalabertlstmmodel
AT didikdwiprasetya sentimentanalysisofemojiandlatinizedarabicinindonesianyoutubecommentsalabertlstmmodel
AT triyannawidiyaningtyas sentimentanalysisofemojiandlatinizedarabicinindonesianyoutubecommentsalabertlstmmodel