A Text Multi-label Classification Scheme Based on Resampling and Ensemble Learning

Tianhao Wang; Tianrang Weng; Jiacheng Ji; Mingjun Zhong; Baili Zhang

doi:10.1007/978-3-031-06761-7_6

A Text Multi-label Classification Scheme Based on Resampling and Ensemble Learning

Tianhao Wang, Tianrang Weng, Jiacheng Ji, Mingjun Zhong, Baili Zhang^*

^*Corresponding author for this work

Southeast University, Nanjing

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Abstract

The medical dispute cases are professional and closely related to medicine. Therefore, the mediation of cases in practice depends heavily on similar historical cases. Multi-label classification of legal documents can efficiently filter irrelevant historical cases, which helps to recommend the similar historical cases faster and better. However, the imbalance and label symbiosis of the data set directly affect multi-label classification of legal documents. Therefore, a multi-label classification scheme based on resampling and ensemble learning is presented in this paper The scheme includes two parts: in the first part, in order to reduce the impact of label symbiosis on resampling, a resampling algorithm based on the average sparsity of the label set is proposed improve the imbalance of the data set; in the second one, a multi-label classification algorithm based on ensemble learning is proposed to train multiple base classifiers and combine each base classifier with a voting strategy of one vote. It can effectively improve the effect of multi-label classification. The experimental results show that the scheme proposed in this paper can improve the effect of multi-label classification and is not only suitable for legal documents but also applicable for other text data sets with imbalanced classes and label symbiosis problems.

Original language	English
Title of host publication	Advances in Artificial Intelligence and Security
Subtitle of host publication	8th International Conference on Artificial Intelligence and Security, ICAIS 2022, Proceedings, Part II
Editors	Xingming Sun, Xiaorui Zhang, Zhihua Xia, Elisa Bertino
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	67-80
Number of pages	14
ISBN (Electronic)	978-3-031-06761-7
ISBN (Print)	9783031067600
DOIs	https://doi.org/10.1007/978-3-031-06761-7_6
Publication status	Published - 8 Jul 2022
Event	8th International Conference on Artificial Intelligence and Security , ICAIS 2022 - Qinghai, China Duration: 15 Jul 2022 → 20 Jul 2022

Publication series

Name	Communications in Computer and Information Science
Volume	1587 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	8th International Conference on Artificial Intelligence and Security , ICAIS 2022
Country/Territory	China
City	Qinghai
Period	15/07/22 → 20/07/22

Bibliographical note

Funding Information:
Acknowledgement. This work was partly supported by the National Key R&D Program of China (2018YFC0830200), the Fundamental Research Funds for the Central Universities (2242018S30021 and 2242017S30023) and Open Research Fund from Key Laboratory of Computer Network and Information Integration in Southeast University, Ministry of Education, China.

Keywords

Class imbalance
Ensemble learning
Label symbiosis
Multi-label classification
Resampling algorithm

Access to Document

10.1007/978-3-031-06761-7_6Licence: Unspecified

Cite this

Wang, T., Weng, T., Ji, J., Zhong, M., & Zhang, B. (2022). A Text Multi-label Classification Scheme Based on Resampling and Ensemble Learning. In X. Sun, X. Zhang, Z. Xia, & E. Bertino (Eds.), Advances in Artificial Intelligence and Security : 8th International Conference on Artificial Intelligence and Security, ICAIS 2022, Proceedings, Part II (pp. 67-80). (Communications in Computer and Information Science; Vol. 1587 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-06761-7_6

A Text Multi-label Classification Scheme Based on Resampling and Ensemble Learning. / Wang, Tianhao; Weng, Tianrang; Ji, Jiacheng et al.
Advances in Artificial Intelligence and Security : 8th International Conference on Artificial Intelligence and Security, ICAIS 2022, Proceedings, Part II. ed. / Xingming Sun; Xiaorui Zhang; Zhihua Xia; Elisa Bertino. Springer Science and Business Media Deutschland GmbH, 2022. p. 67-80 (Communications in Computer and Information Science; Vol. 1587 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Wang, T, Weng, T, Ji, J, Zhong, M & Zhang, B 2022, A Text Multi-label Classification Scheme Based on Resampling and Ensemble Learning. in X Sun, X Zhang, Z Xia & E Bertino (eds), Advances in Artificial Intelligence and Security : 8th International Conference on Artificial Intelligence and Security, ICAIS 2022, Proceedings, Part II. Communications in Computer and Information Science, vol. 1587 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 67-80, 8th International Conference on Artificial Intelligence and Security , ICAIS 2022, Qinghai, China, 15/07/22. https://doi.org/10.1007/978-3-031-06761-7_6

Wang T, Weng T, Ji J, Zhong M, Zhang B. A Text Multi-label Classification Scheme Based on Resampling and Ensemble Learning. In Sun X, Zhang X, Xia Z, Bertino E, editors, Advances in Artificial Intelligence and Security : 8th International Conference on Artificial Intelligence and Security, ICAIS 2022, Proceedings, Part II. Springer Science and Business Media Deutschland GmbH. 2022. p. 67-80. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-06761-7_6

Wang, Tianhao ; Weng, Tianrang ; Ji, Jiacheng et al. / A Text Multi-label Classification Scheme Based on Resampling and Ensemble Learning. Advances in Artificial Intelligence and Security : 8th International Conference on Artificial Intelligence and Security, ICAIS 2022, Proceedings, Part II. editor / Xingming Sun ; Xiaorui Zhang ; Zhihua Xia ; Elisa Bertino. Springer Science and Business Media Deutschland GmbH, 2022. pp. 67-80 (Communications in Computer and Information Science).

@inproceedings{481e5847d9114ab6bdd21241be5ad147,

title = "A Text Multi-label Classification Scheme Based on Resampling and Ensemble Learning",

abstract = "The medical dispute cases are professional and closely related to medicine. Therefore, the mediation of cases in practice depends heavily on similar historical cases. Multi-label classification of legal documents can efficiently filter irrelevant historical cases, which helps to recommend the similar historical cases faster and better. However, the imbalance and label symbiosis of the data set directly affect multi-label classification of legal documents. Therefore, a multi-label classification scheme based on resampling and ensemble learning is presented in this paper The scheme includes two parts: in the first part, in order to reduce the impact of label symbiosis on resampling, a resampling algorithm based on the average sparsity of the label set is proposed improve the imbalance of the data set; in the second one, a multi-label classification algorithm based on ensemble learning is proposed to train multiple base classifiers and combine each base classifier with a voting strategy of one vote. It can effectively improve the effect of multi-label classification. The experimental results show that the scheme proposed in this paper can improve the effect of multi-label classification and is not only suitable for legal documents but also applicable for other text data sets with imbalanced classes and label symbiosis problems.",

keywords = "Class imbalance, Ensemble learning, Label symbiosis, Multi-label classification, Resampling algorithm",

author = "Tianhao Wang and Tianrang Weng and Jiacheng Ji and Mingjun Zhong and Baili Zhang",

note = "Funding Information: Acknowledgement. This work was partly supported by the National Key R&D Program of China (2018YFC0830200), the Fundamental Research Funds for the Central Universities (2242018S30021 and 2242017S30023) and Open Research Fund from Key Laboratory of Computer Network and Information Integration in Southeast University, Ministry of Education, China. ; 8th International Conference on Artificial Intelligence and Security , ICAIS 2022 ; Conference date: 15-07-2022 Through 20-07-2022",

year = "2022",

month = jul,

day = "8",

doi = "10.1007/978-3-031-06761-7_6",

language = "English",

isbn = "9783031067600",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "67--80",

editor = "Xingming Sun and Xiaorui Zhang and Zhihua Xia and Elisa Bertino",

booktitle = "Advances in Artificial Intelligence and Security",

address = "Germany",

}

TY - GEN

T1 - A Text Multi-label Classification Scheme Based on Resampling and Ensemble Learning

AU - Wang, Tianhao

AU - Weng, Tianrang

AU - Ji, Jiacheng

AU - Zhong, Mingjun

AU - Zhang, Baili

N1 - Funding Information: Acknowledgement. This work was partly supported by the National Key R&D Program of China (2018YFC0830200), the Fundamental Research Funds for the Central Universities (2242018S30021 and 2242017S30023) and Open Research Fund from Key Laboratory of Computer Network and Information Integration in Southeast University, Ministry of Education, China.

PY - 2022/7/8

Y1 - 2022/7/8

N2 - The medical dispute cases are professional and closely related to medicine. Therefore, the mediation of cases in practice depends heavily on similar historical cases. Multi-label classification of legal documents can efficiently filter irrelevant historical cases, which helps to recommend the similar historical cases faster and better. However, the imbalance and label symbiosis of the data set directly affect multi-label classification of legal documents. Therefore, a multi-label classification scheme based on resampling and ensemble learning is presented in this paper The scheme includes two parts: in the first part, in order to reduce the impact of label symbiosis on resampling, a resampling algorithm based on the average sparsity of the label set is proposed improve the imbalance of the data set; in the second one, a multi-label classification algorithm based on ensemble learning is proposed to train multiple base classifiers and combine each base classifier with a voting strategy of one vote. It can effectively improve the effect of multi-label classification. The experimental results show that the scheme proposed in this paper can improve the effect of multi-label classification and is not only suitable for legal documents but also applicable for other text data sets with imbalanced classes and label symbiosis problems.

AB - The medical dispute cases are professional and closely related to medicine. Therefore, the mediation of cases in practice depends heavily on similar historical cases. Multi-label classification of legal documents can efficiently filter irrelevant historical cases, which helps to recommend the similar historical cases faster and better. However, the imbalance and label symbiosis of the data set directly affect multi-label classification of legal documents. Therefore, a multi-label classification scheme based on resampling and ensemble learning is presented in this paper The scheme includes two parts: in the first part, in order to reduce the impact of label symbiosis on resampling, a resampling algorithm based on the average sparsity of the label set is proposed improve the imbalance of the data set; in the second one, a multi-label classification algorithm based on ensemble learning is proposed to train multiple base classifiers and combine each base classifier with a voting strategy of one vote. It can effectively improve the effect of multi-label classification. The experimental results show that the scheme proposed in this paper can improve the effect of multi-label classification and is not only suitable for legal documents but also applicable for other text data sets with imbalanced classes and label symbiosis problems.

KW - Class imbalance

KW - Ensemble learning

KW - Label symbiosis

KW - Multi-label classification

KW - Resampling algorithm

UR - http://www.scopus.com/inward/record.url?scp=85135046434&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-06761-7_6

DO - 10.1007/978-3-031-06761-7_6

M3 - Published conference contribution

AN - SCOPUS:85135046434

SN - 9783031067600

T3 - Communications in Computer and Information Science

SP - 67

EP - 80

BT - Advances in Artificial Intelligence and Security

A2 - Sun, Xingming

A2 - Zhang, Xiaorui

A2 - Xia, Zhihua

A2 - Bertino, Elisa

PB - Springer Science and Business Media Deutschland GmbH

T2 - 8th International Conference on Artificial Intelligence and Security , ICAIS 2022

Y2 - 15 July 2022 through 20 July 2022

ER -

A Text Multi-label Classification Scheme Based on Resampling and Ensemble Learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this