RecoMap – a semi-automated tool for analysing railway accident recommendations across jurisdictions and over time
Document Type
Journal Article
Publication Date
2026
Subject Area
place - australasia, place - europe, place - north america, mode - rail, planning - safety/accidents
Keywords
Railway safety, accident investigation, recommendation analysis, structural topic model, learning behaviours
Abstract
Despite many (sometimes similar) recommendations made by independent railway accident investigators across jurisdictions, practitioners continue to suffer from a lack of synthesised recommendations due to the high complexity of analysing textual data. To fill the gap, a semi-automated tool for analysing accident report recommendations, RecoMap, is developed as a framework to help practitioners learn from previous experience. Empirical data is retrieved from official railway accident reports published by Rail Accident Investigation Branch (RAIB), Australian Transport Safety Bureau (ATSB), National Transportation Safety Board (NTSB) and Transportation Safety Board of Canada (TSB). By comparing experiences across countries, this study also identifies a transition from making interfering recommendations addressing operational issues to making supportive recommendations addressing organisational issues in the railway industry. Findings imply that current practices might continue to result in railway accidents that could have been prevented by learning from other jurisdictions and implementing corresponding mitigation measures in advance.
Rights
Permission to publish the abstract has been given by Taylor&Francis, copyright remains with them.
Recommended Citation
Hong, W. T., Clifton, G., & Nelson, J. D. (2026). RecoMap–a semi-automated tool for analysing railway accident recommendations across jurisdictions and over time. Transportation Planning and Technology, 49(2), 145-165.
