Severity Classification Method for Traffic Accident Records Described in Short Sentences

Aiming at the characteristics of urban accident reports in developing countries, the accident severity classification method based on semantic analysis model is proposed, and the process including taxonomy definition, text data preprocessing, word segmentation based on hidden Markov model (HMM), key word selection, weight setting, and classifier construction based on decision tree. The purpose of the model is to lay a data foundation for evaluating the accident loss of descriptive traffic accident records in short sentences. This paper selects the traffic safety management data of Wujiang District of Suzhou City for sample analysis and verifies the accuracy of semantic analysis model by system-error evaluation.

Language

  • English

Media Info

  • Media Type: Web
  • Pagination: pp 4522-4535
  • Monograph Title: CICTP 2020: Transportation Evolution Impacting Future Mobility

Subject/Index Terms

Filing Info

  • Accession Number: 01768468
  • Record Type: Publication
  • ISBN: 9780784483053
  • Files: TRIS, ASCE
  • Created Date: Dec 9 2020 3:07PM