@article{ref1,
title="Application of machine learning to mapping primary causal factors in self reported safety narratives",
journal="Safety science",
year="2015",
author="Robinson, S. D. and Irwin, W. J. and Kelly, T. K. and Wu, X. O.",
volume="75",
number="",
pages="118-129",
abstract="A new method for analysis of text-based reports in accident coding is suggested. This approach utilizes latent semantic analysis to infer higher-order structures between documents and provide an unbiased metric to the narrative analysis process. <br><br>RESULTS from this study on a small sample of aviation safety narratives demonstrates an unsupervised categorization accuracy of 44% for primary-cause within the existing taxonomy. If provided with a large sample set, the indication is that a significant increase in accuracy is possible along with the possibility of recoding between data sets. Demonstrated is the ability of LSA to capture contextual proximity of a narrative.<p />",
language="en",
issn="0925-7535",
doi="10.1016/j.ssci.2015.02.003",
url="http://dx.doi.org/10.1016/j.ssci.2015.02.003"
}