@article{ref1,
title="Identifying low-quality patterns in accidents reports from textual data",
journal="International journal of occupational safety and ergonomics",
year="2022",
author="Macedo, July B. and Ramos, Plinio M. S. and Maior, Caio B. S. and Moura, Márcio J. C. and Lins, Isis D. and Vilela, Romulo F. T.",
volume="ePub",
number="ePub",
pages="ePub-ePub",
abstract="Accident investigation reports provide useful knowledge to support companies to propose preventive and mitigative measures. However, the information presented in accident reports databases is normally large, complex, filled out with errors, missing and/or redundant data. In this paper, we propose text mining and natural language processing techniques to investigate low-quality accident reports. We adopted machine learning (ML) to detect and investigate inconsistencies on accident reports. The methodology was applied on 626 documents collected from an actual hydroelectric power company. The initial ML performances indicated data divergences and concerns related to the report structure. Then, accident database was restructured to more properly form confirming the supposition about the quality of the reports investigated. The proposed approach can be used as a diagnostic tool to improve the design of accident investigation reports to provide a more useful source of knowledge to support decisions in the safety context.<p /> <p>Language: en</p>",
language="en",
issn="1080-3548",
doi="10.1080/10803548.2022.2111847",
url="http://dx.doi.org/10.1080/10803548.2022.2111847"
}