Rumor Detection Based on Attention CNN and Time Series of Context Information

This study aims to explore the time series context and sentiment polarity features of rumors’ life cycles, and how to use them to optimize the CNN model parameters and improve the classification effect. The proposed model is a convolutional neural network embedded with an attention mechanism of sent...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yun Peng, Jianmei Wang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	rumor event detection sentiment polarity time series algorithm attention CNN Information technology T58.5-58.64
Acceso en línea:	https://doaj.org/article/fa0f72e6947640f0891bc0edcf66803b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fa0f72e6947640f0891bc0edcf66803b
record_format	dspace
spelling	oai:doaj.org-article:fa0f72e6947640f0891bc0edcf66803b2021-11-25T17:39:32ZRumor Detection Based on Attention CNN and Time Series of Context Information10.3390/fi131102671999-5903https://doaj.org/article/fa0f72e6947640f0891bc0edcf66803b2021-10-01T00:00:00Zhttps://www.mdpi.com/1999-5903/13/11/267https://doaj.org/toc/1999-5903This study aims to explore the time series context and sentiment polarity features of rumors’ life cycles, and how to use them to optimize the CNN model parameters and improve the classification effect. The proposed model is a convolutional neural network embedded with an attention mechanism of sentiment polarity and time series information. Firstly, the whole life cycle of rumors is divided into 20 groups by the time series algorithm and each group of texts is trained by Doc2Vec to obtain the text vector. Secondly, the SVM algorithm is used to obtain the sentiment polarity features of each group. Lastly, the CNN model with the spatial attention mechanism is used to obtain the rumors’ classification. The experiment results show that the proposed model introduced with features of time series and sentiment polarity is very effective for rumor detection, and can greatly reduce the number of iterations for model training as well. The accuracy, precision, recall and F1 of the attention CNN are better than the latest benchmark model.Yun PengJianmei WangMDPI AGarticlerumor event detectionsentiment polaritytime series algorithmattention CNNInformation technologyT58.5-58.64ENFuture Internet, Vol 13, Iss 267, p 267 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	rumor event detection sentiment polarity time series algorithm attention CNN Information technology T58.5-58.64
spellingShingle	rumor event detection sentiment polarity time series algorithm attention CNN Information technology T58.5-58.64 Yun Peng Jianmei Wang Rumor Detection Based on Attention CNN and Time Series of Context Information
description	This study aims to explore the time series context and sentiment polarity features of rumors’ life cycles, and how to use them to optimize the CNN model parameters and improve the classification effect. The proposed model is a convolutional neural network embedded with an attention mechanism of sentiment polarity and time series information. Firstly, the whole life cycle of rumors is divided into 20 groups by the time series algorithm and each group of texts is trained by Doc2Vec to obtain the text vector. Secondly, the SVM algorithm is used to obtain the sentiment polarity features of each group. Lastly, the CNN model with the spatial attention mechanism is used to obtain the rumors’ classification. The experiment results show that the proposed model introduced with features of time series and sentiment polarity is very effective for rumor detection, and can greatly reduce the number of iterations for model training as well. The accuracy, precision, recall and F1 of the attention CNN are better than the latest benchmark model.
format	article
author	Yun Peng Jianmei Wang
author_facet	Yun Peng Jianmei Wang
author_sort	Yun Peng
title	Rumor Detection Based on Attention CNN and Time Series of Context Information
title_short	Rumor Detection Based on Attention CNN and Time Series of Context Information
title_full	Rumor Detection Based on Attention CNN and Time Series of Context Information
title_fullStr	Rumor Detection Based on Attention CNN and Time Series of Context Information
title_full_unstemmed	Rumor Detection Based on Attention CNN and Time Series of Context Information
title_sort	rumor detection based on attention cnn and time series of context information
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/fa0f72e6947640f0891bc0edcf66803b
work_keys_str_mv	AT yunpeng rumordetectionbasedonattentioncnnandtimeseriesofcontextinformation AT jianmeiwang rumordetectionbasedonattentioncnnandtimeseriesofcontextinformation
_version_	1718412142806302720

Rumor Detection Based on Attention CNN and Time Series of Context Information

Ejemplares similares