Automatic Construction Accident Report Analysis Using Large Language Models (LLMs)
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
Construction site safety is a paramount concern, given the high rate of accidents and fatalities in the sector. This study introduces a novel approach to analyzing construction accident reports by employing advanced Large Language Models (LLMs), specifically GPT-3.5, GPT-4, Gemini Pro, and LLaMA 3. Our research focuses on the classification of key attributes in accident reports: root cause, injury cause, affected body part, severity, and accident time. The results reveal that GPT-4 achieves significantly higher accuracy across most attributes. Gemini Pro demonstrates superior performance in the "Injury Cause" classification, while LLaMA 3 excels in classifying "Severity" and "Root Cause." GPT-3.5, although lagging behind GPT-4, exhibits commendable accuracy. The insights gained from this study are vital for the construction industry, as they indicate the potential for developing more precise and effective safety measures. These findings could lead to a reduction in the frequency and severity of accidents, thereby enhancing worker safety.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Generative models also examined historical accident report data to find patterns and recommend preventive measures (Ahmadi et al., 2024).”
From Artificial intelligence in civil engineering: emerging applications and opportunities (2025) · cites this paper as Ahmadi et al., 2024
In the citing paper
“For example, CNN-based vision systems can identify concrete crack patterns with high accuracy (Ahmadi et al., 2024) and specialized lightweight networks like MobileNetV2 are also effectively used for crack identification on mobile platforms (Hui et al., 2023).”
From Artificial intelligence in civil engineering: emerging applications and opportunities (2025) · cites this paper as Ahmadi et al., 2024
In the citing paper
“Natural language processing (NLP) tools extract information from contracts, reports, and manuals, reducing paperwork bottlenecks and aiding in tasks like the automated analysis of construction accident reports to identify safety patterns (Ahmadi et al., 2024).”
From Artificial intelligence in civil engineering: emerging applications and opportunities (2025) · cites this paper as Ahmadi et al., 2024
In the citing paper
“For instance, a GPT based model has been applied successfully to a constructionaccident reports classification, identifying patterns helpful for safety analysis (Ahmadi et al., 2024).”
From Artificial intelligence in civil engineering: emerging applications and opportunities (2025) · cites this paper as Ahmadi et al., 2024
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Kaugeranna, R., Kaugeranna, E., & Aion, (. S. 4. 6. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.giscience.2023.43 · Cited by 13,690
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
Chain-Of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q. V., & Zhou, D. (2022) · Advances in Neural Information Processing Systems 35 · doi:10.52202/068431-1800 · Cited by 4,505
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Wei, J., Wang, X., Schuurmans, D., Bosma, M., Ichter, B., Xia, F., Chi, E., Le, Q., & Zhou, D. (2022) · arXiv · doi:10.48550/arxiv.2201.11903 · Cited by 4,263
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.18223 · Cited by 2,090
Graph Convolutional Networks for Text Classification
Yao, L., Mao, C., & Luo, Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33017370 · Cited by 1,983
Research works printed but not linked: 7
- 2023, Nearly 3 million people die of work-related accidents and diseases [Online]
- 2023, The center for construction research and training-Construction focus four [Online]
- Radford, 2019, Language models are unsupervised multitask learners
- 2023, OSHA accident report [Online]
- 2024, LlaMA 3.1
- 2024, Ollama
- 2024, Transformers: Documentation
Cited by
Liu, Q., Li, F., Ng, K. K. H., Han, J.-H., & Feng, S. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.126422 · Cited by 73
Artificial intelligence in civil engineering: emerging applications and opportunities
Nyokum, T., & Tamut, Y. (2025) · Frontiers in Built Environment · doi:10.3389/fbuil.2025.1622873 · Cited by 33
Li, F., Su, H., Lee, C., Feng, S., Jiang, Z., & Sun, Z. (2025) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2024.2446511 · Cited by 25
“5, GPT-4, and Gemini Pro) in extracting key information from construction accident reports [20].”
Yang, H., Li, C., & Wang, Q. (2025) · Journal of Loss Prevention in the Process Industries · doi:10.1016/j.jlp.2025.105845 · Cited by 10
Automatic classification of construction accident reports using BERTopic-GLDA approach
Wang, J., Qu, Z., Wu, S., Skitmore, M., & Ma, L. (2025) · Engineering Construction & Architectural Management · doi:10.1108/ecam-04-2025-0692 · Cited by 11
Metadata
- Authors
- Ahmadi, E., Muley, S., & Wang, C.
- Affiliations
- Louisiana State University (US)
- Corresponding author
- Wang, Chao
- Venue
- Journal of Intelligent Construction
- Publisher
- Tsinghua University Press
- Published
- 2025-03
- Volume
- 3
- Issue
- 1
- Pages
- 1-10
- ISSN
- 2958-2652 (ISSN-L)
- 2958-3861
- OpenAlex
- W4399790255
- Cited by
- 35
- References
- 26
- Citations by year
- 2026: 21 · 2025: 14
- FWCI
- 13.93
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- Locations
- Journal of Intelligent Construction (publishedVersion, cc-by)
- Civil War Book Review (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Science Foundation (2222881)
- Topics
- Social Sciences › Safety Research › Occupational Health and Safety Research
- Physical Sciences › Computer Science › Artificial Intelligence › Text and Document Classification Technologies
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- construction accidents, large language models, construction safety, accident severity, GPT-4, Gemini Pro, Llama 3, GPT-3.5, occupational safety
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Automatic Construction Accident Report Analysis Using Large Language Models (LLMs). https://app.cochat.ai/papers/10.26599/jic.2024.9180039
- The paper
- Ahmadi, E., Muley, S., & Wang, C. (2025). Automatic Construction Accident Report Analysis Using Large Language Models (LLMs). Journal of Intelligent Construction. https://doi.org/10.26599/jic.2024.9180039
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.