Objectives. The mining sector is a hazardous work environment with high accident rates, causing human suffering and financial losses. Examining incident reports is crucial for preventing comparable events; however, manual classification of large accident datasets is labour-intensive and time-consuming. Methods. This work presents a novel methodology for classifying fatal accident reports using text-mining techniques. It uses natural language processing techniques to transform textual data into a vector representation. Stratified 10-fold cross-validation ensures training and test sets maintain equivalent class distributions from the original dataset, improving model performance. Six supervised machine learning models - logistic regression, support vector machine (SVM), random forest, naïve Bayes, decision tree and multilayer perceptron (MLP) - were employed to classify 1308 fatal accident records into eight accident types. Results. The analysis demonstrates strong model accuracy. The MLP model achieved superior overall performance with a 0.84 weighted average F1 score, followed by logistic regression (0.83), SVM (0.81), random forest (0.73), naïve Bayes (0.65) and decision tree (0.57). Conclusion. This study presents an automated system for identifying accident types from incident reports. The proposed approach reduces misclassifications and mitigates human biases in incident report analysis, offering a reliable tool for mining safety management.
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.
6 October 2026 in International Journal of System Assurance Engineering and Management