Graph-based joint pandemic concern and relation extraction on Twitter

作者：

Highlights：

• The inherent features captured by concern graph for improving the model performance.

• A novel deep learning model for sequential and regional dependency feature learning.

• A novel end-to-end model for concerns and relations extraction.

• Generic and effective concerns extraction evaluated by using real-world data.

摘要

•The inherent features captured by concern graph for improving the model performance.•A novel deep learning model for sequential and regional dependency feature learning.•A novel end-to-end model for concerns and relations extraction.•Generic and effective concerns extraction evaluated by using real-world data.

论文关键词：Concern detection,COVID-19,Auto concern extraction,Concern graph,Graph Convolutional Network

论文评审过程：Received 22 June 2021, Revised 28 December 2021, Accepted 9 January 2022, Available online 29 January 2022, Version of Record 2 February 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116538