Construction accident narrative classification: An evaluation of text mining techniques

• Published in: Accident analysis and prevention Vol. 108; pp. 122 - 130
• Main Authors: Goh, Yang Miang, Ubeynarayana, C.U.
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01-11-2017
• Subjects: Accident classification; Accidents; Accidents, Occupational - classification; Algorithms; Bayes Theorem; Construction Industry; Construction safety; Data mining; Data Mining - methods; Databases, Factual; Decision Trees; Humans; Linear Models; Machine Learning - standards; Narration; Reproducibility of Results; Safety; Support Vector Machine; Text mining; Text mining; Construction safety; Support vector machine; Data mining; Accident classification
• ISSN: 0001-4575; 1879-2057
• DOI: 10.1016/j.aap.2017.08.026

•Evaluated six machine learning algorithms for classifying accident narratives in accordance to 11 accident types.•Found that support vector machine (SVM) produced the best performance.•Across the 11 accident types, the average precision of the SVM was 0.73, average recall was 0.63, and average F1 score was 0.67.•Commonly mislabeled cases were evaluated using confusion matrix, and qualitative evaluation of mislabeled cases.•A set of 1,000 labelled accident narratives and more than 3,000 unlabeled narratives were made available publicly.
Learning from past accidents is fundamental to accident prevention. Thus, accident and near miss reporting are encouraged by organizations and regulators. However, for organizations managing large safety databases, the time taken to accurately classify accident and near miss narratives will be very significant. This study aims to evaluate the utility of various text mining classification techniques in classifying 1000 publicly available construction accident narratives obtained from the US OSHA website. The study evaluated six machine learning algorithms, including support vector machine (SVM), linear regression (LR), random forest (RF), k-nearest neighbor (KNN), decision tree (DT) and Naive Bayes (NB), and found that SVM produced the best performance in classifying the test set of 251 cases. Further experimentation with tokenization of the processed text and non-linear SVM were also conducted. In addition, a grid search was conducted on the hyperparameters of the SVM models. It was found that the best performing classifiers were linear SVM with unigram tokenization and radial basis function (RBF) SVM with uni-gram tokenization. In view of its relative simplicity, the linear SVM is recommended. Across the 11 labels of accident causes or types, the precision of the linear SVM ranged from 0.5 to 1, recall ranged from 0.36 to 0.9 and F1 score was between 0.45 and 0.92. The reasons for misclassification were discussed and suggestions on ways to improve the performance were provided.