AUTHOR=Khairuddin Mohamed Zul Fadhli , Hasikin Khairunnisa , Abd Razak Nasrul Anuar , Lai Khin Wee , Osman Mohd Zamri , Aslan Muhammet Fatih , Sabanci Kadir , Azizan Muhammad Mokhzaini , Satapathy Suresh Chandra , Wu Xiang 

TITLE=Predicting occupational injury causal factors using text-based analytics: A systematic review

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.984099

DOI=10.3389/fpubh.2022.984099

ISSN=2296-2565

ABSTRACT=The workplace accidents can cause a catastrophic loss to the company including human injuries and fatalities. Occupational injury reports may provide the detailed description on how the incidents occurred. Thus, the narrative is a useful information to extract, classify and analyze the occupational injury. This study provides a systematic review of text mining and natural language processing (NLP) application to extract the occupational injury reports. A systematic searching was conducted through multiple databases including Scopus, PubMed and Science Direct. Only original studies that examined the application of machine and deep learning-based natural language processing models for occupational injury analysis were incorporated in this study. A total of 27, out of 210 articles were reviewed in this study by adopting the Preferred Reporting Items for Systematic Review (PRISMA). The review has highlighted that various machine and deep learning-based NLP models were applied such as K-means, Naïve Bayes, Support Vector Machine, Decision Tree, K-Nearest Neighbors including deep neural networks in classifying the type of accidents, identifying the causal factors, as well as, predicting the occupational injury. However, there is a paucity in using the deep learning models in extracting the occupational injury reports. Despite that, this paper believed that there is a huge and promising potential to explore the application of NLP and text-based analytics in this occupational injury research field. Therefore, the improvement of data balancing techniques and development of an automated decision-making support system for occupational injury by applying the deep learning-based NLP models are the recommendations given for future research.