Multi-label disaster text classification via supervised contrastive learning for social media data. (December 2022)

• Record Type: Journal Article
• Authors: Xie, Shaorong; Hou, Chunning; Yu, Hang; Zhang, Zhenyu; Luo, Xiangfeng; Zhu, Nengjun
• Is Part Of: Computers & electrical engineering. Volume 104:Part A(2022)
• Publication Date: 2022-12
• Subjects: Disasters -- Contrastive learning -- Multi-label -- Text classification; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108401
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Social media is a crucial way to release information in a timely manner during disasters, which provides help to people who suffer from disasters. In this disaster information, each message may contain multiple labels. The single-label classification method cannot be adapted to a multi-label classification problem. In addition, there is a lack of representative baseline datasets due to the differences between disaster data sources. We propose a supervised contrastive learning based multi-label classification framework as a general framework for data processing and model training. Specifically, it learns features of disaster data and identifies different disaster type information, then trains a multi-label classification model of disaster texts in different dimensions. The results of empirical studies on three disaster text classification datasets show that this method can effectively improve the accuracy of the model and the representation ability of semantic information. Highlights: A supervised contrastive learning-based multi-label classification framework is proposed to solve disaster text classification problem. Two multi-label disaster datasets for social media are built as benchmark datasets. The effectiveness of the proposed model is validated by different comparison experiments.