TARU PUBLICATIONS
Journal of Information and Optimization Sciences cover
Open Access ·Peer-reviewed·ISSN (Online): 2169-0103·ISSN (Print): 0252-2667

WoS  JIF 2026 : 0.4 (Q4)

Powered by:Powered by

Monthly Journal: Publishes theoretical and applied research on topics in information and optimization sciences.

Issues up to 2022 co-published with and available at:Taylor & Francis
submissions@tarupublications.com
Open Access Research Article

Integrating text mining and Bayesian networks for root-cause identification of near-miss incidents to enhance safety measures

* , , ,

* Corresponding author · click or hover a name for details

pp. 1–32Online FirstJuly 2026DOI: 10.47974/JIOS-2189XML
Received:
02 Dec 2024
Published Online:
15 Jul 2026
Article type:
Research Article
Language:
EN
Article no.:
JIOS-2189
Pages:
1–32

Abstract

Near-miss incidents (as leading safety indicators) provide implicit signals regarding the various limitations of the prevalent safety management system at a workplace. Implementing proactive safety measures requires the identification of root causes and, therefore, warrants in-depth analysis of these near-miss incidents. Effective root-cause management is crucial to avoid these incidents and improve overall safety. However, identifying root causes from the raw text-based near-miss incident reports is challenging because they are unstructured. To this purpose, we provide a methodology that combines text mining and Bayesian Networks to identify root causes and develop a casual knowledge model. The developed model has been used to analyse seven near-miss incident scenarios for validation. The findings indicate that incidents are more likely to occur due to factors such as defective switches or cables, poor stair or floor conditions, damaged wires, ropes, or slings, unsafe crane operations, malfunctioning valves or hoses, and the involvement of heavy vehicles like trucks and dumpers during loading or transportation activities. This work contributes to dealing with narrative text data and raising the organisation’s awareness of various circumstances in which these incidents occur.

Keywords

Subject Classifications

Primary 68T50Secondary 62F15

References

[1] A. Verma, S. Das Khan, J. Maiti, and O. B. Krishna, “Identifying patterns of safety related incidents in a steel plant using association rule mining of incident investigation reports,” Saf. Sci., vol. 70, pp. 89–98 (Dec. 2014).
[2] A. Verma and J. Maiti, “Text-document clustering-based cause and effect analysis methodology for steel plant incident data,” Int. J. Inj. Contr. Saf. Promot., vol. 25, no. 4, pp. 416–426 (2018), doi: 10.1080/17457300.2018.1456468.
[3] K. Singh, J. Maiti, and K. Dhalmahapatra, “Chain of events model for safety management: Data analytics approach,” Saf. Sci., vol. 118, pp. 568–582 (2019).
[4] A. Bagga, S. Srivastava, and R. S. Shekhawat, “Prediction of road crash attributes using machine learning,” J. Inf. Optim. Sci., vol. 45, no. 4, pp. 1217–1227 (2024).
[5] T. W. Van Der Schaaf, “Near miss reporting in the chemical process industry,” Eindhoven University of Technology (1992).
[6] J. R. Phimister, U. Oktem, P. R. Kleindorfer, and H. Kunreuther, “Near-miss incident management in the chemical process industry.,” Risk Anal., vol. 23, no. 3, pp. 445–59 (Jun. 2003).
[7] U. G. Oktem, “Near-Miss : A Tool for Integrated Safety , Health , Environmental and Security Management,” (2003).
[8] F. E. Bird and G. L. Germain, Loss control management: Practical Loss Control Leadership, Revised Ed. International Loss Control Institute Loganville (1986).
[9] H. . Heinrich, Industrial Accident Prevention, Second. New York: McGraw-Hill (1959).
[10] A. Verma, D. Rajput, and J. Maiti, “Prioritization of Near-Miss Incidents Using Text Mining and Bayesian Network,” Int. Conf. Adv. Comput. Data Sci., vol. 721, pp. 183–191 (2017).
[11] U. G. Oktem, R. Wong, and C. Oktem, “Near-Miss Management : Managing the Bottom of the Risk Pyramid,” Risk & Regulation-Magazine of the ESRC Centre for Analysis of Risk and Regulation, no. July, pp. 12–13 (2010).
[12] M. G. Gnoni, S. Andriulo, G. Maggio, and P. Nardone, “‘ Lean occupational’ safety: An application for a Near-miss Management System design,” Saf. Sci., vol. 53, pp. 96–104 (2013).
[13] B. Basso, C. Carpegna, C. Dibitonto, G. Gaido, A. Robotto, and C. Zonato, “Reviewing the safety management system by incident investigation and performance indicators,” J. Loss Prev. Process Ind., vol. 17, no. 3, pp. 225–231 (May 2004).
[14] Z. Nivolianitou, M. Konstandinidou, C. Kiranoudis, and N. Markatos, “Development of a database for accidents and incidents in the Greek petrochemical industry,” J. Loss Prev. Process Ind., vol. 19, no. 6, pp. 630–638 (Nov. 2006).
[15] T. van der Schaaf and L. Kanse, “Biases in incident reporting databases: an empirical study in the chemical process industry,” Saf. Sci., vol. 42, no. 1, pp. 57–67 (Jan. 2004).
[16] W. Wu, H. Yang, D. a. S. Chew, S. Yang, A. G. F. Gibb, and Q. Li, “Towards an autonomous real-time tracking system of near-miss accidents on construction sites,” Autom. Constr., vol. 19, no. 2, pp. 134–141 (Mar. 2010).
[17] W. Wu, A. G. F. Gibb, and Q. Li, “Accident precursors and near misses on construction sites: An investigative tool to derive information from accident databases,” Saf. Sci., vol. 48, no. 7, pp. 845–858 (Aug. 2010).
[18] F. B. Cambraia, T. A. Saurin, and C. T. Formoso, “Identification, analysis and dissemination of information on near misses: A case study in the construction industry,” Saf. Sci., vol. 48, no. 1, pp. 91–99 (Jan. 2010).
[19] M. S. Brian Thoroman and P. Salmon, “An integrated approach to near miss analysis combining AcciMap and Network Analysis,” Saf. Sci., vol. 130, no. June, p. 104859 (2020).
[20] R. L. Dillon and C. H. Tinsley, “How Near-Misses Influence Decision Making Under Risk: A Missed Opportunity for Learning,” Manage. Sci., vol. 54, no. 8, pp. 1425–1440 (Aug. 2008).
[21] S. Jones, C. Kirchsteiger, and W. Bjerke, “The importance of near miss reporting to further improve safety performance,” J. Loss Prev. Process Ind., vol. 12, no. 1, pp. 59–67 (Jan. 1999), doi: 10.1016/S0950-4230(98)00038-2.
[22] P. Marsh and D. Kendrick, “Near miss and minor injury information--can it be used to plan and evaluate injury prevention programmes?,” Accid. Anal. Prev., vol. 32, no. 3, pp. 345–54 (May 2000).
[23] A. Verma, J. Maiti, and V. N. Gaikwad, “A preliminary analysis of incident investigation reports of an integrated steel plant: some reflection,” Int. J. Inj. Contr. Saf. Promot., vol. 25, no. 2, pp. 180–194 (2018).
[24] M. G. Gnoni and G. Lettera, “Near-miss management systems: A methodological comparison,” J. Loss Prev. Process Ind., vol. 25, no. 3, pp. 609–616 (May 2012).
[25] S. J. Dee, B. L. Cox, and R. A. Ogle, “Using Near Misses to Improve Risk Management Decisions,” Process Saf. Prog., vol. 32, no. 4 (2013).
[26] J. a. Taylor, A. V. Lacovara, G. S. Smith, R. Pandian, and M. Lehto, “Near-miss narratives from the fire service: A Bayesian analysis,” Accid. Anal. Prev., vol. 62, pp. 119–129 (2014), doi: 10.1016/j.aap.2013.09.012.
[27] E. Fersini, E. Messina, and F. a. Pozzi, “Sentiment analysis: Bayesian Ensemble Learning,” Decis. Support Syst., vol. 68, pp. 26–38 (2014).
[28] R. P. Chaturvedi and U. Ghose, “Small object detection using retinanet with hybrid anchor box hyper tuning using interface of Bayesian mathematics,” J. Inf. Optim. Sci., vol. 43, no. 8, pp. 2099–2110 (2022).
[29] M. Neil, N. Fenton, and M. Tailor, “Using Bayesian networks to model expected and unexpected operational losses,” Risk Anal., vol. 25, no. 4, pp. 963–972 (2005).
[30] V. M. Bier and A. Mosleh, “The analysis of accident precursors and near misses: Implications for risk assessment and risk management,” Reliab. Eng. Syst. Saf., vol. 27, no. 1, pp. 91–101 (1990).
[31] A. Meel and W. D. Seider, “Plant-specific dynamic failure assessment using Bayesian theory,” Chem. Eng. Sci., vol. 61, no. 21, pp. 7036–7056 (Nov. 2006), doi: 10.1016/j.ces.2006.07.007.
[32] E. Lee, Y. Park, and J. G. Shin, “Large engineering project risk management using a Bayesian belief network,” Expert Syst. Appl., vol. 36, no. 3, pp. 5880–5887 (Apr. 2009).
[33] G. Kabir, S. Tesfamariam, A. Francisque, and R. Sadiq, “Evaluating risk of water mains failure using a Bayesian belief network model,” Eur. J. Oper. Res., vol. 240, no. 1, pp. 220–234 (2015).
[34] S. Park, H. Yang, G. Heo, M. Zubair, and R. K. Ur, “Study on Nuclear Accident Precursors Using AHP and BBN,” Sci. Technol. Nucl. Install., vol. 2014, p. 12 (2014).
[35] M. Zubair, S. Park, G. Heo, M. U. Hassan, and M. Aamir, “Study on nuclear accident precursors using AHP and BBN, a case study of Fukushima accident,” Int. J. energy Res., vol. 39, no. 1, pp. 98–110 (2015).
[36] A. Verma, K. Dhalmahapatra, and J. Maiti, “Forecasting occupational safety performance and mining text-based association rules for incident occurrences,” Saf. Sci., vol. 159, no. August 2022, p. 106014 (2023).
[37] J. Pearl, Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc. (1988).
[38] M. Arias, F. Díez, and M. Palacios, “OpenMarkovXML. A format for encoding probabilistic graphical models,” (2010).
[39] M. Tiwari, P. Aital, and P. Joshi, “A comprehensive survey and review of machine learning techniques in document processing : Industry applications and future directions,” J. Inf. Optim. Sci., vol. 45, no. 4, pp. 1177–1188 (2024).
[40] M. Williamsen, “Near-Miss Reporting: A missing link in safety culture,” Prof. Saf., vol. 58, no. May, pp. 46–50 (2013).

Views: 140Downloads: 76Citations: 0