ระบบจัดเก็บและค้นหางานวิจัยอัจฉริยะ

BERTGRU4Sentiment: Bidirectional Encoder Representations from Transformers with Gated Recurrent Unit for Multilingual Sentiment Analysis

ผศ.ดร.นิกร กรรณิกากลาง | Sentiment Analysis BERT GRU

จำนวนผู้เข้าชม

1,105

BERTGRU4Sentiment: Bidirectional Encoder Representations from Transformers with Gated Recurrent Unit for Multilingual Sentiment Analysis

ดาวน์โหลดเอกสาร

ดาวน์โหลด: 20 ครั้ง

DOI Link

Collection	RMUTK Research Repository (RMUTK IR) บทความประชุมวิชาการ — Proceedings
ID RMUTK Digital	RMUTK000050
Title	BERTGRU4Sentiment: Bidirectional Encoder Representations from Transformers with Gated Recurrent Unit for Multilingual Sentiment Analysis
Alternative title	BERTGRU4Sentiment: Bidirectional Encoder Representations from Transformers with Gated Recurrent Unit for Multilingual Sentiment Analysis
Authors	ผศ.ดร.นิกร กรรณิกากลาง ผู้แต่งหลัก
Faculty	คณะบริหารธุรกิจ
Volume / Issue / Pages	pp.77-85
Conference	12th International Conference on Creative Technology (CreTech2026)
Conference Date	2026-08-08
Conference Location	โรงแรมแกรนด์ พาลาสโซ่ พัทยา จังหวัดชลบุรี
Year	2569
Level	ระดับนานาชาติ
DOI	-
ISBN / ISSN	-
Funding Source	มทร.กรุงเทพ
Abstract	This study proposes BERTGRU4Sentiment, a deep learning model that combines fine-tuned Bidirectional Encoder Representations from Transformers (BERT) with a Gated Recurrent Unit (GRU) for multilingual sentiment analysis. The proposed model is evaluated on four benchmark datasets: Wongnai (Thai), Amazon Reviews (English), Twitter/X (English), and IMDB (English), covering both three-class (negative, neutral, positive) and two-class (negative, positive) classification tasks. To address class imbalance, a mixed over- and under-sampling strategy is applied to all datasets. Results demonstrate that BERTGRU4Sentiment consistently outperforms traditional baseline models including Decision Tree, Random Forest, XGBoost, and LSTM across all datasets, achieving accuracy of 69.49% on Wongnai, 93.67% on Amazon Reviews, 71.73% on Twitter, and 83.97% on IMDB. The findings confirm that BERTGRU4Sentiment enables richer contextual feature extraction, and the proposed architecture is effective for multilingual sentiment classification tasks.
Abstract (EN)	This study proposes BERTGRU4Sentiment, a deep learning model that combines fine-tuned Bidirectional Encoder Representations from Transformers (BERT) with a Gated Recurrent Unit (GRU) for multilingual sentiment analysis. The proposed model is evaluated on four benchmark datasets: Wongnai (Thai), Amazon Reviews (English), Twitter/X (English), and IMDB (English), covering both three-class (negative, neutral, positive) and two-class (negative, positive) classification tasks. To address class imbalance, a mixed over- and under-sampling strategy is applied to all datasets. Results demonstrate that BERTGRU4Sentiment consistently outperforms traditional baseline models including Decision Tree, Random Forest, XGBoost, and LSTM across all datasets, achieving accuracy of 69.49% on Wongnai, 93.67% on Amazon Reviews, 71.73% on Twitter, and 83.97% on IMDB. The findings confirm that BERTGRU4Sentiment enables richer contextual feature extraction, and the proposed architecture is effective for multilingual sentiment classification tasks.
Keywords (TH)	Sentiment Analysis BERT GRU Deep Learning Natural Language Processing Multilingual
Keywords (EN)	Sentiment Analysis BERT GRU Deep Learning Natural Language Processing Multilingual
Access Level	Open Access (เปิดสาธารณะ)

เอกสารดิจิทัล

RMUTK000050_full.pdf

จำนวนดาวน์โหลด: 20 ครั้ง

Open Access

ดาวน์โหลด