Research on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching

Abstract Due to its potential impact on business efficiency, automated customer complaint labeling and classification are of great importance for management decision making and business applications. The majority of the current research on automated labeling uses large and well-balanced datasets. Ho...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiaobo Tang, Hao Mou, Jiangnan Liu, Xin Du
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/352a9258216e459f8c23e5b357b6bc17
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:352a9258216e459f8c23e5b357b6bc17
record_format	dspace
spelling	oai:doaj.org-article:352a9258216e459f8c23e5b357b6bc172021-12-02T17:51:21ZResearch on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching10.1038/s41598-021-91189-02045-2322https://doaj.org/article/352a9258216e459f8c23e5b357b6bc172021-06-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-91189-0https://doaj.org/toc/2045-2322Abstract Due to its potential impact on business efficiency, automated customer complaint labeling and classification are of great importance for management decision making and business applications. The majority of the current research on automated labeling uses large and well-balanced datasets. However, customer complaint labels are hierarchical in structure, with many labels at the lowest hierarchy level. Relying on lower-level labels leads to small and imbalanced samples, thus rendering the current automatic labeling practices inapplicable to customer complaints. This article proposes an automatic labeling model incorporating the BERT and word2vec methods. The model is validated on electric utility customer complaint data. Within the model, the BERT method serves to obtain shallow text tags. Furthermore, text enhancement is used to mitigate the problem of imbalanced samples that emerge when the number of labels is large. Finally, the word2vec model is utilized for deep text analysis. Experiments demonstrate the proposed model's efficiency in automating customer complaint labeling. Consequently, the proposed model supports enterprises in improving their service quality while simultaneously reducing labor costs.Xiaobo TangHao MouJiangnan LiuXin DuNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Xiaobo Tang Hao Mou Jiangnan Liu Xin Du Research on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching
description	Abstract Due to its potential impact on business efficiency, automated customer complaint labeling and classification are of great importance for management decision making and business applications. The majority of the current research on automated labeling uses large and well-balanced datasets. However, customer complaint labels are hierarchical in structure, with many labels at the lowest hierarchy level. Relying on lower-level labels leads to small and imbalanced samples, thus rendering the current automatic labeling practices inapplicable to customer complaints. This article proposes an automatic labeling model incorporating the BERT and word2vec methods. The model is validated on electric utility customer complaint data. Within the model, the BERT method serves to obtain shallow text tags. Furthermore, text enhancement is used to mitigate the problem of imbalanced samples that emerge when the number of labels is large. Finally, the word2vec model is utilized for deep text analysis. Experiments demonstrate the proposed model's efficiency in automating customer complaint labeling. Consequently, the proposed model supports enterprises in improving their service quality while simultaneously reducing labor costs.
format	article
author	Xiaobo Tang Hao Mou Jiangnan Liu Xin Du
author_facet	Xiaobo Tang Hao Mou Jiangnan Liu Xin Du
author_sort	Xiaobo Tang
title	Research on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching
title_short	Research on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching
title_full	Research on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching
title_fullStr	Research on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching
title_full_unstemmed	Research on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching
title_sort	research on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/352a9258216e459f8c23e5b357b6bc17
work_keys_str_mv	AT xiaobotang researchonautomaticlabelingofimbalancedtextsofcustomercomplaintsbasedontextenhancementandlayerbylayersemanticmatching AT haomou researchonautomaticlabelingofimbalancedtextsofcustomercomplaintsbasedontextenhancementandlayerbylayersemanticmatching AT jiangnanliu researchonautomaticlabelingofimbalancedtextsofcustomercomplaintsbasedontextenhancementandlayerbylayersemanticmatching AT xindu researchonautomaticlabelingofimbalancedtextsofcustomercomplaintsbasedontextenhancementandlayerbylayersemanticmatching
_version_	1718379277406175232

Research on automatic labeling of imbalanced texts of customer complaints based on text enhancement and layer-by-layer semantic matching

Ejemplares similares