A Natural Language Processing-Based Classification and Mode-Based Ranking of Musculoskeletal Disorder Risk Factors

TL;DR

This research delves into Musculoskeletal Disorder risk factors, using a blend of Natural Language Processing (NLP) and mode-based ranking, which enhances MSD comprehension and informs occupational health strategies.

Abstract

This research delves into Musculoskeletal Disorder (MSD) risk factors, using a blend of Natural Language Processing (NLP) and mode-based ranking. The aim is to refine understanding, classification, and prioritization for focused prevention and treatment. Eight NLP models are evaluated, combining pre-trained transformers, cosine similarity, and distance metrics to categorize factors into personal, biomechanical, workplace, psychological, and organizational classes. BERT with cosine similarity achieves 28% accuracy; sentence transformer with Euclidean, Bray-Curtis, and Minkowski distances scores 100%. With 10-fold cross-validation, statistical tests ensure robust results. Survey data and mode-based ranking determine severity hierarchy, aligning with the literature. "Working posture" is the most severe, highlighting posture's role. Survey insights emphasize "Job insecurity," "Effort reward imbalance," and "Poor employee facility" as significant contributors. Rankings offer actionable insights for MSD prevention. The study suggests targeted interventions, workplace improvements, and future research directions. This integrated NLP and ranking approach enhances MSD comprehension and informs occupational health strategies.

Figures (5)

• Figure 1: Methodological framework illustrating NLP-based risk factor classification (left) and statistical mode-based risk factor ranking (right).
• Figure 2: Confusion matrices for 8 NLP models employed for risk factor classification, including BERT + cosine similarity measure, cosine similarity measure, Manhattan distance measure, NLTK + Jaccard similarity measure, Euclidean distance measure, Mahalanobis distance measure, Bray-Curtis distance measure, and Minkowski distance measure, listed from top left to bottom right.
• Figure 3: Classification reports for 8 NLP models employed for risk factor classification, including BERT + cosine similarity measure, cosine similarity measure, Manhattan distance measure, NLTK + Jaccard similarity measure, Euclidean distance measure, Mahalanobis distance measure, Bray-Curtis distance measure, and Minkowski distance measure, listed from top left to bottom right.
• Figure 4: Distribution of severity rankings of the MSD risk factors on the numerical scale ranging from 1 to 25.
• Figure 5: Precision, Recall, and F1-score comparison among the implemented NLP models.