Dean Bowman

TL;DR: The proposition that manual content analysis of injury reports can be eliminated using natural language processing (NLP) is tested and the results indicate that the NLP system is capable of quickly and automatically scanning unstructured injury reports for 101 attributes and outcomes with over 95% accuracy.

TL;DR: Two state-of-the-art ML models, Random Forest and Stochastic Gradient Tree Boosting, were applied to a data set of carefully featured attributes and categorical safety outcomes, extracted from a large pool of textual construction injury reports via a highly accurate Natural Language Processing tool developed by past research.

TL;DR: A newly introduced conceptual framework and accompanying natural language processing system is used to extract standard information in the form of fundamental attributes from a set of raw accident reports, then applied state-of-the-art data mining techniques to discover attribute combinations that contribute to injuries.