From free-text to structured safety management: Introduction of a semi-automated classification method of railway hazard reports to elements on a bow-tie diagram

Abstract This paper introduces a semi-automated technique for classifying text-based close call reports from the GB railway industry. The classification schema uses natural language processing techniques to classify close call reports in accordance with the threat pathways shown on bow-tie diagrams. The method enables categorisation of a very large number of unstructured text documents where safety-related information has not previously been extracted due to the infeasibility of analysis by human readers. The results demonstrate mixed accuracy in the categorisation of close calls, with the highest accuracy being for the threat pathways that are more frequently reported. This work paves the way to machine-assisted analysis of text-based safety and risk databases, and provides a step forward in the introduction of data analytics in the safety and risk domain. Others working in this area have speculated that approaches such as this could be mandatory for safety management in the future.

[1]  Maria Grazia Gnoni,et al.  Measuring the effectiveness of a near-miss management system: An application in an automotive firm supplier , 2014, Reliab. Eng. Syst. Saf..

[2]  Maria Grazia Gnoni,et al.  Near-miss management systems: A methodological comparison , 2012 .

[3]  Jiyi Li Domain specific commonsense relation extraction from bag of concepts metadata , 2015, IMCOM.

[4]  Ken Thompson,et al.  Programming Techniques: Regular expression search algorithm , 1968, Commun. ACM.

[5]  Simon Jones,et al.  The importance of near miss reporting to further improve safety performance , 1999 .

[6]  Ute Hoffmann Techniques Of Safety Management , 2016 .

[7]  Robin L. Dillon,et al.  How Near-Misses Influence Decision Making Under Risk: A Missed Opportunity for Learning , 2008, Manag. Sci..

[8]  Antonis Targoutzidis Incorporating human factors into a simplified "bow-tie" approach for workplace risk assessment. , 2010 .

[9]  Carlos T. Formoso,et al.  Identification, analysis and dissemination of information on near misses: A case study in the construction industry , 2010 .

[10]  Matthew R. Hallowell,et al.  Automated content analysis for construction safety: A natural language processing system to extract precursors and outcomes from unstructured injury reports , 2016 .

[11]  Maria Grazia Gnoni,et al.  “Lean occupational” safety: An application for a Near-miss Management System design , 2013 .

[12]  Gilbert L. Peterson,et al.  Applicability of Latent Dirichlet Allocation to multi-disk search , 2014, Digit. Investig..

[13]  Nahla Ben Amor,et al.  A new multi-objectives approach to implement preventive and protective barriers in bow tie diagram , 2014 .

[14]  Raghu Raman,et al.  Process Systems Risk Management , 2013 .

[15]  Martyn Ramsden,et al.  Bowtie diagrams: A user-friendly risk communication tool , 2017 .

[16]  Miguel Figueres-Esteban,et al.  Learning from text-based close call data , 2016 .

[17]  Son Doan,et al.  Application of information technology: MedEx: a medication information extraction system for clinical narratives , 2010, J. Am. Medical Informatics Assoc..

[18]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[19]  Rui Yan,et al.  How Transferable are Neural Networks in NLP Applications? , 2016, EMNLP.

[20]  Rafael Valencia-García,et al.  Ontology learning from biomedical natural language documents using UMLS , 2011, Expert Syst. Appl..

[21]  David Sánchez,et al.  Domain Ontology Learning from the Web , 2007, The Knowledge Engineering Review.

[22]  Dan S. Nielsen The cause/consequence diagram method as a basis for quantitative accident analysis , 1971 .

[23]  James P. Bliss,et al.  What are close calls? A proposed taxonomy to inform risk communication research , 2014 .

[24]  George L. Germain,et al.  Damage control : a new horizon in accident prevention and cost improvement , 1966 .

[25]  Coen Van Gulijk,et al.  The potential of ontology for safety and risk analysis , 2016 .

[26]  Linda Wright,et al.  Accident versus near miss causation: a critical review of the literature, an empirical test in the UK railway domain, and their implications for other sectors. , 2004, Journal of hazardous materials.

[27]  J. P. Visser,et al.  Developments in HSE Management in Oil and Gas Exploration and Production , 1998 .

[28]  Patrick Thomas Hudson Integrating organisational culture into incident analyses: Extending the Bow Tie model , 2010 .

[29]  Hinrich Schütze,et al.  Book Reviews: Foundations of Statistical Natural Language Processing , 1999, CL.