A novel classification approach based on context connotative network (CCNet): A case of construction site accidents

作者：

Highlights：

• A new architecture CCNet: Content Connotative Network is proposed.

• This method combines Convolution, Long Short-Term Memory, and Attention networks to form a hybrid structure.

• Preprocessing techniques like Lemmatization, Chunking, TSNE, and GloVe are employed to capture semantic relationships.

• The proposed methodology outperforms conventional algorithms.

摘要

•A new architecture CCNet: Content Connotative Network is proposed.•This method combines Convolution, Long Short-Term Memory, and Attention networks to form a hybrid structure.•Preprocessing techniques like Lemmatization, Chunking, TSNE, and GloVe are employed to capture semantic relationships.•The proposed methodology outperforms conventional algorithms.

论文关键词：Construction accident reports classification,Deep learning,GloVe,Attention,Noun and verb phrases

论文评审过程：Received 19 July 2021, Revised 30 October 2021, Accepted 19 April 2022, Available online 25 April 2022, Version of Record 5 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117281