Deep learning model with hierarchical attention mechanism for sentiment classification of Vietnamese comments

Q3 Physics and Astronomy Cybernetics and Physics Pub Date : 2023-09-30 DOI:10.35470/2226-4116-2023-12-2-111-120
Luu Van Huy, Ngo Le Huy Hien, Nguyen Thi Hoang Phuong, Nguyen Van Hieu
{"title":"Deep learning model with hierarchical attention mechanism for sentiment classification of Vietnamese comments","authors":"Luu Van Huy, Ngo Le Huy Hien, Nguyen Thi Hoang Phuong, Nguyen Van Hieu","doi":"10.35470/2226-4116-2023-12-2-111-120","DOIUrl":null,"url":null,"abstract":"In the current digital era, text documents become valuable for businesses to reach potential customers and curtail advertising costs. However, extracting and classifying beneficial information from texts can prove challenging and time-consuming, particularly in complex languages like Vietnamese. This study aims to classify the sentiment of Vietnamese comments on e-commerce websites into negative and positive classes. To enhance the performance of sentiment classification, the study fine-tuned traditional models of Convolutional Neural Networks and Recurrent Neural Networks (RNN). Then, this research proposed a combination of RNN and attention mechanisms at the word and word-and-sentence levels of the input document. The results showed an impressive accuracy of 93.72% and an F1 score of 93.7% on the RNN model with a word-and-sentence-level attention mechanism. This research outcome contributes to the field of text classification and could be applied in opinion mining, customer feedback analysis, and natural language processing. Future work aims to enhance sentiment analysis accuracy and expand the models’ scope to encompass more languages.","PeriodicalId":37674,"journal":{"name":"Cybernetics and Physics","volume":"26 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cybernetics and Physics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.35470/2226-4116-2023-12-2-111-120","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Physics and Astronomy","Score":null,"Total":0}
引用次数: 0

Abstract

In the current digital era, text documents become valuable for businesses to reach potential customers and curtail advertising costs. However, extracting and classifying beneficial information from texts can prove challenging and time-consuming, particularly in complex languages like Vietnamese. This study aims to classify the sentiment of Vietnamese comments on e-commerce websites into negative and positive classes. To enhance the performance of sentiment classification, the study fine-tuned traditional models of Convolutional Neural Networks and Recurrent Neural Networks (RNN). Then, this research proposed a combination of RNN and attention mechanisms at the word and word-and-sentence levels of the input document. The results showed an impressive accuracy of 93.72% and an F1 score of 93.7% on the RNN model with a word-and-sentence-level attention mechanism. This research outcome contributes to the field of text classification and could be applied in opinion mining, customer feedback analysis, and natural language processing. Future work aims to enhance sentiment analysis accuracy and expand the models’ scope to encompass more languages.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于层次注意机制的越南语评论情感分类深度学习模型
在当前的数字时代,文本文档对于企业接触潜在客户和减少广告成本变得很有价值。然而,从文本中提取和分类有益的信息可能是具有挑战性和耗时的,特别是在越南语等复杂语言中。本研究旨在将越南人在电子商务网站上的评论情绪分为消极和积极两类。为了提高情感分类的性能,本研究对传统的卷积神经网络和递归神经网络模型进行了微调。然后,本研究在输入文档的单词和单词-句子层面提出了RNN与注意机制的结合。结果表明,在单词-句子级注意机制的RNN模型上,准确率达到了93.72%,F1得分达到了93.7%。该研究成果为文本分类领域做出了贡献,可应用于意见挖掘、客户反馈分析和自然语言处理等领域。未来的工作旨在提高情感分析的准确性,并扩大模型的范围,以涵盖更多的语言。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Cybernetics and Physics
Cybernetics and Physics Chemical Engineering-Fluid Flow and Transfer Processes
CiteScore
1.70
自引率
0.00%
发文量
17
审稿时长
10 weeks
期刊介绍: The scope of the journal includes: -Nonlinear dynamics and control -Complexity and self-organization -Control of oscillations -Control of chaos and bifurcations -Control in thermodynamics -Control of flows and turbulence -Information Physics -Cyber-physical systems -Modeling and identification of physical systems -Quantum information and control -Analysis and control of complex networks -Synchronization of systems and networks -Control of mechanical and micromechanical systems -Dynamics and control of plasma, beams, lasers, nanostructures -Applications of cybernetic methods in chemistry, biology, other natural sciences The papers in cybernetics with physical flavor as well as the papers in physics with cybernetic flavor are welcome. Cybernetics is assumed to include, in addition to control, such areas as estimation, filtering, optimization, identification, information theory, pattern recognition and other related areas.
期刊最新文献
Enhancing functionality of two-rotor vibration machine by automatic control Adaptive exchange protocol for multi-agent communication in augmented reality system Feasibility study of permanent magnet dipoles for SILA facility Digital control of the synchronous modes of the two-rotor vibration set-up Suitability of different machine learning methods for high-speed flow modeling issues
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1