Relational Graph Convolutional Network for Text-Mining-Based Accident Causal Classification
Accident investigation reports are text documents that systematically review and analyze the cause and process of accidents after accidents have occurred and have been widely used in the fields such as transportation, construction and aerospace. With the aid of accident investigation reports, the ca...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/5/2482 |
| _version_ | 1827651954141036544 |
|---|---|
| author | Zaili Chen Kai Huang Li Wu Zhenyu Zhong Zeyu Jiao |
| author_facet | Zaili Chen Kai Huang Li Wu Zhenyu Zhong Zeyu Jiao |
| author_sort | Zaili Chen |
| collection | DOAJ |
| description | Accident investigation reports are text documents that systematically review and analyze the cause and process of accidents after accidents have occurred and have been widely used in the fields such as transportation, construction and aerospace. With the aid of accident investigation reports, the cause of the accident can be clearly identified, which provides an important basis for accident prevention and reliability assessment. However, since accident record reports are mostly composed of unstructured data such as text, the analysis of accident causes inevitably relies on a lot of expert experience and statistical analyses also require a lot of manual classification. Although, in recent years, with the development of natural language processing technology, there have been many efforts to automatically analyze and classify text. However, the existing methods either rely on large corpus and data preprocessing methods, which are cumbersome, or extract text information based on bidirectional encoder representation from transformers (BERT), but the computational cost is extremely high. These shortcomings make it still a great challenge to automatically analyze accident investigation reports and extract the information therein. To address the aforementioned problems, this study proposes a text-mining-based accident causal classification method based on a relational graph convolutional network (R-GCN) and pre-trained BERT. On the one hand, the proposed method avoids preprocessing such as stop word removal and word segmentation, which not only preserves the information of accident investigation reports to the greatest extent, but also avoids tedious operations. On the other hand, with the help of R-GCN to process the semantic features obtained by BERT representation, the dependence of BERT retraining on computing resources can be avoided. |
| first_indexed | 2024-03-09T20:47:47Z |
| format | Article |
| id | doaj.art-8e4da6053d0149b388df970ca23d3930 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T20:47:47Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-8e4da6053d0149b388df970ca23d39302023-11-23T22:41:33ZengMDPI AGApplied Sciences2076-34172022-02-01125248210.3390/app12052482Relational Graph Convolutional Network for Text-Mining-Based Accident Causal ClassificationZaili Chen0Kai Huang1Li Wu2Zhenyu Zhong3Zeyu Jiao4Faculty of Engineering, China University of Geosciences, Wuhan 430074, ChinaGuangdong Key Laboratory of Modern Control Technology, Institute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangzhou 510070, ChinaFaculty of Engineering, China University of Geosciences, Wuhan 430074, ChinaFaculty of Engineering, China University of Geosciences, Wuhan 430074, ChinaGuangdong Key Laboratory of Modern Control Technology, Institute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangzhou 510070, ChinaAccident investigation reports are text documents that systematically review and analyze the cause and process of accidents after accidents have occurred and have been widely used in the fields such as transportation, construction and aerospace. With the aid of accident investigation reports, the cause of the accident can be clearly identified, which provides an important basis for accident prevention and reliability assessment. However, since accident record reports are mostly composed of unstructured data such as text, the analysis of accident causes inevitably relies on a lot of expert experience and statistical analyses also require a lot of manual classification. Although, in recent years, with the development of natural language processing technology, there have been many efforts to automatically analyze and classify text. However, the existing methods either rely on large corpus and data preprocessing methods, which are cumbersome, or extract text information based on bidirectional encoder representation from transformers (BERT), but the computational cost is extremely high. These shortcomings make it still a great challenge to automatically analyze accident investigation reports and extract the information therein. To address the aforementioned problems, this study proposes a text-mining-based accident causal classification method based on a relational graph convolutional network (R-GCN) and pre-trained BERT. On the one hand, the proposed method avoids preprocessing such as stop word removal and word segmentation, which not only preserves the information of accident investigation reports to the greatest extent, but also avoids tedious operations. On the other hand, with the help of R-GCN to process the semantic features obtained by BERT representation, the dependence of BERT retraining on computing resources can be avoided.https://www.mdpi.com/2076-3417/12/5/2482accident causal classificationaccident investigation reportstext miningR-GCNBERT |
| spellingShingle | Zaili Chen Kai Huang Li Wu Zhenyu Zhong Zeyu Jiao Relational Graph Convolutional Network for Text-Mining-Based Accident Causal Classification Applied Sciences accident causal classification accident investigation reports text mining R-GCN BERT |
| title | Relational Graph Convolutional Network for Text-Mining-Based Accident Causal Classification |
| title_full | Relational Graph Convolutional Network for Text-Mining-Based Accident Causal Classification |
| title_fullStr | Relational Graph Convolutional Network for Text-Mining-Based Accident Causal Classification |
| title_full_unstemmed | Relational Graph Convolutional Network for Text-Mining-Based Accident Causal Classification |
| title_short | Relational Graph Convolutional Network for Text-Mining-Based Accident Causal Classification |
| title_sort | relational graph convolutional network for text mining based accident causal classification |
| topic | accident causal classification accident investigation reports text mining R-GCN BERT |
| url | https://www.mdpi.com/2076-3417/12/5/2482 |
| work_keys_str_mv | AT zailichen relationalgraphconvolutionalnetworkfortextminingbasedaccidentcausalclassification AT kaihuang relationalgraphconvolutionalnetworkfortextminingbasedaccidentcausalclassification AT liwu relationalgraphconvolutionalnetworkfortextminingbasedaccidentcausalclassification AT zhenyuzhong relationalgraphconvolutionalnetworkfortextminingbasedaccidentcausalclassification AT zeyujiao relationalgraphconvolutionalnetworkfortextminingbasedaccidentcausalclassification |