Weibo Text Sentiment Analysis Based on BERT and Deep Learning

With the rapid increase of public opinion data, the technology of Weibo text sentiment analysis plays a more and more significant role in monitoring network public opinion. Due to the sparseness and high-dimensionality of text data and the complex semantics of natural language, sentiment analysis ta...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hongchan Li, Yu Ma, Zishuai Ma, Haodong Zhu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	BERT sentiment analysis Weibo text word vector deep learning Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/fcb8c50d425f4fe995f0db38901c7749
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fcb8c50d425f4fe995f0db38901c7749
record_format	dspace
spelling	oai:doaj.org-article:fcb8c50d425f4fe995f0db38901c77492021-11-25T16:37:49ZWeibo Text Sentiment Analysis Based on BERT and Deep Learning10.3390/app1122107742076-3417https://doaj.org/article/fcb8c50d425f4fe995f0db38901c77492021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10774https://doaj.org/toc/2076-3417With the rapid increase of public opinion data, the technology of Weibo text sentiment analysis plays a more and more significant role in monitoring network public opinion. Due to the sparseness and high-dimensionality of text data and the complex semantics of natural language, sentiment analysis tasks face tremendous challenges. To solve the above problems, this paper proposes a new model based on BERT and deep learning for Weibo text sentiment analysis. Specifically, first using BERT to represent the text with dynamic word vectors and using the processed sentiment dictionary to enhance the sentiment features of the vectors; then adopting the BiLSTM to extract the contextual features of the text, the processed vector representation is weighted by the attention mechanism. After weighting, using the CNN to extract the important local sentiment features in the text, finally the processed sentiment feature representation is classified. A comparative experiment was conducted on the Weibo text dataset collected during the COVID-19 epidemic; the results showed that the performance of the proposed model was significantly improved compared with other similar models.Hongchan LiYu MaZishuai MaHaodong ZhuMDPI AGarticleBERTsentiment analysisWeibo textword vectordeep learningTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10774, p 10774 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	BERT sentiment analysis Weibo text word vector deep learning Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	BERT sentiment analysis Weibo text word vector deep learning Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Hongchan Li Yu Ma Zishuai Ma Haodong Zhu Weibo Text Sentiment Analysis Based on BERT and Deep Learning
description	With the rapid increase of public opinion data, the technology of Weibo text sentiment analysis plays a more and more significant role in monitoring network public opinion. Due to the sparseness and high-dimensionality of text data and the complex semantics of natural language, sentiment analysis tasks face tremendous challenges. To solve the above problems, this paper proposes a new model based on BERT and deep learning for Weibo text sentiment analysis. Specifically, first using BERT to represent the text with dynamic word vectors and using the processed sentiment dictionary to enhance the sentiment features of the vectors; then adopting the BiLSTM to extract the contextual features of the text, the processed vector representation is weighted by the attention mechanism. After weighting, using the CNN to extract the important local sentiment features in the text, finally the processed sentiment feature representation is classified. A comparative experiment was conducted on the Weibo text dataset collected during the COVID-19 epidemic; the results showed that the performance of the proposed model was significantly improved compared with other similar models.
format	article
author	Hongchan Li Yu Ma Zishuai Ma Haodong Zhu
author_facet	Hongchan Li Yu Ma Zishuai Ma Haodong Zhu
author_sort	Hongchan Li
title	Weibo Text Sentiment Analysis Based on BERT and Deep Learning
title_short	Weibo Text Sentiment Analysis Based on BERT and Deep Learning
title_full	Weibo Text Sentiment Analysis Based on BERT and Deep Learning
title_fullStr	Weibo Text Sentiment Analysis Based on BERT and Deep Learning
title_full_unstemmed	Weibo Text Sentiment Analysis Based on BERT and Deep Learning
title_sort	weibo text sentiment analysis based on bert and deep learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/fcb8c50d425f4fe995f0db38901c7749
work_keys_str_mv	AT hongchanli weibotextsentimentanalysisbasedonbertanddeeplearning AT yuma weibotextsentimentanalysisbasedonbertanddeeplearning AT zishuaima weibotextsentimentanalysisbasedonbertanddeeplearning AT haodongzhu weibotextsentimentanalysisbasedonbertanddeeplearning
_version_	1718413115054358528

Weibo Text Sentiment Analysis Based on BERT and Deep Learning

Ejemplares similares