IDEAS home Printed from https://ideas.repec.org/a/sae/risrel/v238y2024i5p957-971.html
   My bibliography  Save this article

A framework based on Natural Language Processing and Machine Learning for the classification of the severity of road accidents from reports

Author

Listed:
  • Dario Valcamonico
  • Piero Baraldi
  • Francesco Amigoni
  • Enrico Zio

Abstract

Road safety analysis is typically performed by domain experts on the basis of the information contained in accident reports. The main challenges are the difficulty of considering a large number of reports in textual form and the subjectivity of the expert judgments contained in reports. This work develops a framework based on the combination of Natural Language Processing (NLP) and Machine Learning (ML) for the automatic classification of accidents with the final aim of assisting experts in performing road safety analyses. Two different models for the representation of the textual reports (Hierarchical Dirichlet Processes (HDPs) and Doc2vec) and three ML-based classifiers (Artificial Neural Networks (ANNs), Decision Trees (DTs) and Random Forests (RFs)) are compared. The framework is applied to a repository of road accident reports provided by the US National Highway Traffic Safety Administration. The best trade-off between accuracy of the classification and explainability of the obtained results is achieved by combining HDP topic modeling and RF classification.

Suggested Citation

  • Dario Valcamonico & Piero Baraldi & Francesco Amigoni & Enrico Zio, 2024. "A framework based on Natural Language Processing and Machine Learning for the classification of the severity of road accidents from reports," Journal of Risk and Reliability, , vol. 238(5), pages 957-971, October.
  • Handle: RePEc:sae:risrel:v:238:y:2024:i:5:p:957-971
    DOI: 10.1177/1748006X221140196
    as

    Download full text from publisher

    File URL: https://journals.sagepub.com/doi/10.1177/1748006X221140196
    Download Restriction: no

    File URL: https://libkey.io/10.1177/1748006X221140196?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Teh, Yee Whye & Jordan, Michael I. & Beal, Matthew J. & Blei, David M., 2006. "Hierarchical Dirichlet Processes," Journal of the American Statistical Association, American Statistical Association, vol. 101, pages 1566-1581, December.
    2. Yang, Zhe & Baraldi, Piero & Zio, Enrico, 2020. "A novel method for maintenance record clustering and its application to a case study of maintenance optimization," Reliability Engineering and System Safety, Elsevier, vol. 203(C).
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Michelle Dietzen & Haoran Zhai & Olivia Lucas & Oriol Pich & Christopher Barrington & Wei-Ting Lu & Sophia Ward & Yanping Guo & Robert E. Hynds & Simone Zaccaria & Charles Swanton & Nicholas McGranaha, 2024. "Replication timing alterations are associated with mutation acquisition during breast and lung cancer evolution," Nature Communications, Nature, vol. 15(1), pages 1-23, December.
    2. Redivo, Edoardo & Nguyen, Hien D. & Gupta, Mayetri, 2020. "Bayesian clustering of skewed and multimodal data using geometric skewed normal distributions," Computational Statistics & Data Analysis, Elsevier, vol. 152(C).
    3. Parvin Ahmadi & Iman Gholampour & Mahmoud Tabandeh, 2018. "Cluster-based sparse topical coding for topic mining and document clustering," Advances in Data Analysis and Classification, Springer;German Classification Society - Gesellschaft für Klassifikation (GfKl);Japanese Classification Society (JCS);Classification and Data Analysis Group of the Italian Statistical Society (CLADAG);International Federation of Classification Societies (IFCS), vol. 12(3), pages 537-558, September.
    4. Jeffrey L. Furman & Florenta Teodoridis, 2020. "Automation, Research Technology, and Researchers’ Trajectories: Evidence from Computer Science and Electrical Engineering," Organization Science, INFORMS, vol. 31(2), pages 330-354, March.
    5. Shu-Ping Shi & Yong Song, 2012. "Identifying Speculative Bubbles with an Infinite Hidden Markov Model," Working Paper series 26_12, Rimini Centre for Economic Analysis.
    6. Jin, Xin & Maheu, John M. & Yang, Qiao, 2022. "Infinite Markov pooling of predictive distributions," Journal of Econometrics, Elsevier, vol. 228(2), pages 302-321.
    7. Gustaf Bellstam & Sanjai Bhagat & J. Anthony Cookson, 2021. "A Text-Based Analysis of Corporate Innovation," Management Science, INFORMS, vol. 67(7), pages 4004-4031, July.
    8. Hassan Akell & Farkhondeh-Alsadat Sajadi & Iraj Kazemi, 2023. "Construction of Jointly Distributed Random Samples Drawn from the Beta Two-Parameter Process," Methodology and Computing in Applied Probability, Springer, vol. 25(3), pages 1-12, September.
    9. Hongxia Yang & Aurelie Lozano, 2015. "Multi-relational learning via hierarchical nonparametric Bayesian collective matrix factorization," Journal of Applied Statistics, Taylor & Francis Journals, vol. 42(5), pages 1133-1147, May.
    10. Bauwens, Luc & Dufays, Arnaud & Rombouts, Jeroen V.K., 2014. "Marginal likelihood for Markov-switching and change-point GARCH models," Journal of Econometrics, Elsevier, vol. 178(P3), pages 508-522.
    11. Robert M. Dorazio & Bhramar Mukherjee & Li Zhang & Malay Ghosh & Howard L. Jelks & Frank Jordan, 2008. "Modeling Unobserved Sources of Heterogeneity in Animal Abundance Using a Dirichlet Process Prior," Biometrics, The International Biometric Society, vol. 64(2), pages 635-644, June.
    12. Jeong Hwan Kook & Michele Guindani & Linlin Zhang & Marina Vannucci, 2019. "NPBayes-fMRI: Non-parametric Bayesian General Linear Models for Single- and Multi-Subject fMRI Data," Statistics in Biosciences, Springer;International Chinese Statistical Association, vol. 11(1), pages 3-21, April.
    13. Yong Song, 2014. "Modelling Regime Switching And Structural Breaks With An Infinite Hidden Markov Model," Journal of Applied Econometrics, John Wiley & Sons, Ltd., vol. 29(5), pages 825-842, August.
    14. Lu Shaochuan, 2023. "Scalable Bayesian Multiple Changepoint Detection via Auxiliary Uniformisation," International Statistical Review, International Statistical Institute, vol. 91(1), pages 88-113, April.
    15. Braga, Joaquim A.P. & Andrade, António R., 2021. "Multivariate statistical aggregation and dimensionality reduction techniques to improve monitoring and maintenance in railways: The wheelset component," Reliability Engineering and System Safety, Elsevier, vol. 216(C).
    16. Michael Stewart & Melinda Hodkiewicz & Wei Liu & Tim French, 2024. "MWO2KG and Echidna: Constructing and exploring knowledge graphs from maintenance data," Journal of Risk and Reliability, , vol. 238(5), pages 920-932, October.
    17. Ying Liao & Yisha Xiang & Min Wang, 2021. "Health assessment and prognostics based on higher‐order hidden semi‐Markov models," Naval Research Logistics (NRL), John Wiley & Sons, vol. 68(2), pages 259-276, March.
    18. Markus Jochmann, 2015. "Modeling U.S. Inflation Dynamics: A Bayesian Nonparametric Approach," Econometric Reviews, Taylor & Francis Journals, vol. 34(5), pages 537-558, May.
    19. Evelina Gabasova & John Reid & Lorenz Wernisch, 2017. "Clusternomics: Integrative context-dependent clustering for heterogeneous datasets," PLOS Computational Biology, Public Library of Science, vol. 13(10), pages 1-29, October.
    20. Yoshi Fujiwara & Rubaiyat Islam, 2021. "Bitcoin's Crypto Flow Network," Papers 2106.11446, arXiv.org, revised Jul 2021.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:sae:risrel:v:238:y:2024:i:5:p:957-971. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: SAGE Publications (email available below). General contact details of provider: .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.