Predicting Fatal Mine Accident Categories Using Text Mining and Machine Learning: A Comparative Model Analysis

The threat of mine accidents continues to endanger workers worldwide, so proper classification of accidents becomes essential for developing specific prevention measures. The research focuses on advancing reactive safety practices because prediction models must identify upcoming accident types during planning. Our method combines machine learning with text mining techniques to examine historical fatal accident reports using approaches that have not yet been included in mining safety literature. A statistical model prediction pipeline has been established to study fatal accident reports using natural language processing (NLP) with vectorisation techniques and six machine learning (ML) algorithms: logistic regression (LR), support vector machine (SVM), random forest (RF), naïve Bayes (NB), decision tree (DT), and multilayer perceptron (MLP) algorithms with stratified 10-fold cross validation. We evaluated the performance using the confusion matrix, precision, recall, and weighted average F1 scores revealed that the MLP model achieved superior performance (0.84 F1 score), followed by LR (0.83), SVM (0.81), RF (0.70), NB (0.60), and DT (0.57). The innovative aspect of this study is its use of complete text mining techniques against unstructured accident reports, which enables detection capabilities that typical structured data evaluation methods cannot achieve. Research shows that Natural Language Processing (NLP) and Machine Learning (ML) integrated systems create exceptional improvements in accident predictions. Mining safety authorities and stakeholders now have evidence-based prevention tools that aid the development of focused safety initiatives to lower mining-related deaths.