Classifying OSHA construction accident reports: leveraging ensemble learning and lightweight large language models (l-LLMs)
Identification
- Public canonical key
- radar:r-288252b6cd1acb6d09cbde1e0bb234c8
- Authors
- Jun Wang · Shujie Wu · Ziyi Qu · Jianhong Shen · Shoeb Ahmed Memon · Martin Skitmore · Leyuan Ma
- Reported year
- 2025
- Reported language
- en
- Source type
- article
- First detected
- 2026-11-14T02:04:08.693339+00:00
- Last metadata observation
- 2026-11-14T02:04:08.693339+00:00
- Last HTTP verification
- Not checked
Institutions reported by the source
Qingdao University of Technology · Bond University
Reported affiliation countries
AU · CN
Documentary abstract — original language
Purpose This study aims to enhance the classification of construction accident reports by addressing challenges including limited high-quality datasets, class imbalance and constraints of traditional machine learning models. A novel framework integrating ensemble learning with lightweight large language models (l-LLMs) is proposed to improve the accuracy, robustness and practical utility of safety management in the construction industry. Design/methodology/approach A dataset of 10,994 Occupational Safety and Health Administration (OSHA) construction accident reports was manually labeled using the Occupational Injury and Illness Classification System (OIICS). To address class imbalance, random oversampling and Synthetic Minority Oversampling Technique (SMOTE) were applied and compared. Five l-LLMs (TinyBERT, MobileBERT, ELECTRA, DistilBERT and ALBERT) were fine-tuned for classification, and three ensemble methods (soft voting, hard voting and stacking) were evaluated. Findings Random oversampling substantially improved performance, whereas SMOTE decreased effectiveness. Ensemble classifiers consistently outperformed individual large language models (LLMs), with the soft-voting ensemble achieving the highest F1 score (0.9261 ± 0.0063), surpassing baseline models support vector machine (SVM), Naïve Bayes (NB) and long short-term memory (LSTM) network. The results demonstrate the framework’s ability to accurately classify rare and complex accident types, supporting early hazard detection, targeted safety training and risk mitigation strategies. Originality/value The study advances construction safety analytics by integrating ensemble learning with l-LLMs, offering a robust solution for imbalanced textual datasets. It highlights practical applications, including enhanced safety management, decision support and accident prevention, with potential adaptation to other datasets and international contexts. By linking technical innovation to tangible societal and economic benefits, the framework contributes to safer, more efficient construction practices and promotes a culture of safety.
Identifiers
- OPENALEX
- https://openalex.org/W7117466637
- DOI
- 10.1108/ecam-08-2025-1273
Documentary context
- Documentary family
- article
- Source-reported types
- article
- Publishers
- Emerald Publishing Limited
Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.
Sources
OpenAlex · Record 1
Cite this reference
Jun Wang; Shujie Wu; Ziyi Qu; Jianhong Shen; Shoeb Ahmed Memon; Martin Skitmore; Leyuan Ma. Classifying OSHA construction accident reports: leveraging ensemble learning and lightweight large language models (l-LLMs). 2025. https://doi.org/10.1108/ecam-08-2025-1273
JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·
APA, Chicago, ISO 690: bibliographic formats using available fields. OSCOLA / Bluebook: structured data only; full legal citation compliance is not claimed without verification of required elements.
- APA
- Jun Wang; Shujie Wu; Ziyi Qu; Jianhong Shen; Shoeb Ahmed Memon; Martin Skitmore; Leyuan Ma. (2025). Classifying OSHA construction accident reports: leveraging ensemble learning and lightweight large language models (l-LLMs). https://doi.org/10.1108/ecam-08-2025-1273
- Chicago
- Jun Wang; Shujie Wu; Ziyi Qu; Jianhong Shen; Shoeb Ahmed Memon; Martin Skitmore; Leyuan Ma. Classifying OSHA construction accident reports: leveraging ensemble learning and lightweight large language models (l-LLMs). 2025. https://doi.org/10.1108/ecam-08-2025-1273
- ISO 690
- Jun Wang; Shujie Wu; Ziyi Qu; Jianhong Shen; Shoeb Ahmed Memon; Martin Skitmore; Leyuan Ma. Classifying OSHA construction accident reports: leveraging ensemble learning and lightweight large language models (l-LLMs). 2025. https://doi.org/10.1108/ecam-08-2025-1273
Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31
UDTR Global Rights of Nature Legal Library. Classifying OSHA construction accident reports: leveraging ensemble learning and lightweight large language models (l-LLMs). Documentary record: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-288252b6cd1acb6d09cbde1e0bb234c8/ · Last HTTP verification: not performed
Research dossiers and documentary relations
Source roles
Bibliographic / original publication source · https://doi.org/10.1108/ecam-08-2025-1273
An authority link alone does not verify a legal claim. Abstracts and full texts remain subject to their source terms.
Documentary status
Relevance pending
Library
This identity is not yet included in the Legal Library.