Text-Mining Based Risk Source Identification Model for Transportation Safety

In order to solve data deficiency and excessive staff workload in the risk-source identification of road transportation safety, an automatic identification model is proposed from the angle of text mining. Firstly, the model performs feature enhancement preprocessing operation through the causality sentence extraction and extracted sentence segmentation. Secondly, the feature construction adapted to the convolutional neural network (CNN) is conducted, which contains word information and position information. Thirdly, the results of feature construction feed into the CNN to realize the identification of risk sources. Finally, experiments are conducted with the data sets of traffic accidents, demonstrating that the proposed model can identify most of risk sources for road transportation safety with the accuracy of about 77.321%.