Highlights Accident narratives are studied for automatic coding with machine learning. Body part(s), source, event, hospitalization, and amputation are considered. Word embeddings approaches are utilized to classify accident narratives. BERT word embeddings outperform competing approaches. Trained models generalize well in two transfer learning contexts.

    Abstract Introduction: Ensuring occupational health and safety is an enormous concern for organizations, as accidents not only harm workers but also result in financial losses. Analysis of accident data has the potential to reveal insights that may improve capabilities to mitigate future accidents. However, because accident data are often transcribed textually, analyzing these narratives proves difficult. This study contributes to a recent stream of literature utilizing machine learning to automatically label accident narratives, converting them into more easily analyzable fields. Method: First, a large dataset of accident narratives in which workers were injured is collected from the U.S. Occupational Safety and Health Administration (OSHA). Word embeddings-based text mining is implemented; compared to past works, this methodology offers excellent performance. Second, to improve the richness of analyses, each record is assessed across five dimensions. The machine learning models provide classifications of body part(s) injured, the source of the injury, the type of event causing the injury, whether a hospitalization occurred, and whether an amputation occurred. Finally, demonstrating generalizability, the trained models are deployed to analyze two additional datasets of accident narratives in the construction industry and the mining and metals industry (transfer learning). Practical Applications: These contributions improve organizations’ capacities to rapidly analyze textual accident narratives.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Characterizing accident narratives with word embeddings: Improving accuracy, richness, and generalizability


    Beteiligte:

    Erschienen in:

    Erscheinungsdatum :

    2021-12-20


    Format / Umfang :

    15 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Exploring Earth Science Applications using Word Embeddings

    Derek Koehl / Udaysankur Nair / Rahul Ramachandran et al. | NTRS


    METHOD FOR IMPROVING ACCURACY OF POSITIONING TRAFFIC ACCIDENT SITE

    LV WEITAO / PENG PEIYAN / JIANG LILI et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    A Bayesian approach to quantifying uncertainties and improving generalizability in traffic prediction models

    Sengupta, Agnimitra / Mondal, Sudeepta / Das, Adway et al. | Elsevier | 2024


    Enhancing generalizability of machine-learning turbulence models

    Li, Jiaqi / Bin, Yuanwei / Huang, George et al. | AIAA | 2024


    System for determining occurrence of an automobile accident and characterizing the accident

    RISHI SUNIJA / RISHI SUMIT / KOCHHAR AYUSH et al. | Europäisches Patentamt | 2020

    Freier Zugriff