Natural Language Processing for the identification of Human factors in aviation accidents causes: An application to the SHEL methodology

Accidents in aviation are rare events. From them, aviation safety management systems take fast and effective remedy actions by performing the analysis of the root causes of accidents, most of which are proved to be human factors. Since the current standard relies on the manual classification performed by trained staff, there are no technical standards already defined for automated human factors identification. This paper considers this issue, proposing machine learning techniques by leveraging on the state-of-the-art technologies of Natural Language Processing. The techniques are then adapted to the Software Hardware Environment Liveware (SHEL) standard accident causality model and tested on a set of real accidents. The computational results show the accuracy and effectiveness of the proposed methodology. Furthermore, the application of the methodology to real documents checked by experts estimates a reduction of the time needed for at least 30% compared to the standard methods of human factors identification.

Automated summary

This study focuses on the human factors as the main causes of aviation accidents, and proposes a machine learning approach using natural language processing technology to identify human factors. Results from testing on real accidents demonstrate the accuracy and effectiveness of the method, estimating a reduction of at least 30% in the time needed for human factors identification compared to standard methods.