TY - JOUR
T1 - A Novel and Intelligent Safety-Hazard Classification Method with Syntactic and Semantic Features for Large-Scale Construction Projects
AU - Tian, Dan
AU - Li, Mingchao
AU - Han, Shuai
AU - Shen, Yang
N1 - Funding Information:
This research was supported by the National Natural Science Foundation of China (Grant 52179139) and the Open Fund of Hubei Key Laboratory of Construction and Management in Hydropower Engineering (Grant 2020KSD05).
Publisher Copyright:
© 2022 American Society of Civil Engineers.
PY - 2022/10/1
Y1 - 2022/10/1
N2 - To improve the efficiency of safety management, it is important to classify massive and complex construction site safety hazard texts in large-scale projects. High-precision safety hazard text classification is a lengthy and challenging process. Most existing safety hazard text classification methods capture semantic information using machine learning or deep learning, ignoring the syntactic dependency between words. However, syntactic dependency contains rich structural information that is useful to alleviate information loss and enrich text features. To address these issues, this study proposes a graph structure-based hybrid deep learning method to achieve the automatic classification of large-scale project safety hazard texts. The method uses syntactic dependency and Bidirectional Encoder Representation from Transformers to express the syntactic structure and semantic information of text, and a graph structure fusing the syntactic structure and semantic information is constructed to quantify text information. Further, an encoding-decoding mechanism is built using a graph convolutional neural network and bidirectional long short-term memory to address graph structure data and classify safety hazard texts. Our proposed method is used to classify hydraulic engineering construction safety hazard texts, and the classification accuracy reaches 86.56%. Meanwhile, the experimental results demonstrate that our model achieves superior performance compared to existing methods. This proves the ability of our model to capture and analyze text information and verifies the reliability and effectiveness of this method in large-scale project safety hazard management.
AB - To improve the efficiency of safety management, it is important to classify massive and complex construction site safety hazard texts in large-scale projects. High-precision safety hazard text classification is a lengthy and challenging process. Most existing safety hazard text classification methods capture semantic information using machine learning or deep learning, ignoring the syntactic dependency between words. However, syntactic dependency contains rich structural information that is useful to alleviate information loss and enrich text features. To address these issues, this study proposes a graph structure-based hybrid deep learning method to achieve the automatic classification of large-scale project safety hazard texts. The method uses syntactic dependency and Bidirectional Encoder Representation from Transformers to express the syntactic structure and semantic information of text, and a graph structure fusing the syntactic structure and semantic information is constructed to quantify text information. Further, an encoding-decoding mechanism is built using a graph convolutional neural network and bidirectional long short-term memory to address graph structure data and classify safety hazard texts. Our proposed method is used to classify hydraulic engineering construction safety hazard texts, and the classification accuracy reaches 86.56%. Meanwhile, the experimental results demonstrate that our model achieves superior performance compared to existing methods. This proves the ability of our model to capture and analyze text information and verifies the reliability and effectiveness of this method in large-scale project safety hazard management.
KW - Bidirectional Encoder Representations from Transformers (BERT)
KW - Bidirectional long short-term memory (BiLSTM)
KW - Construction safety hazard
KW - Graph convolutional network (GCN)
KW - Graph structure
KW - Large-scale project
KW - Text classification
UR - http://www.scopus.com/inward/record.url?scp=85135458755&partnerID=8YFLogxK
U2 - 10.1061/(ASCE)CO.1943-7862.0002382
DO - 10.1061/(ASCE)CO.1943-7862.0002382
M3 - Journal article
AN - SCOPUS:85135458755
SN - 0733-9364
VL - 148
JO - Journal of Construction Engineering and Management
JF - Journal of Construction Engineering and Management
IS - 10
M1 - 04022109
ER -