Highway Construction Safety Analysis Using Large Language Models
Open accessThe DOI matches its Crossref record; 37 of the 38 references it cites were found in a registry or an index.
Abstract
The highway construction industry carries substantial safety risks for workers, necessitating thorough accident analyses to implement effective preventive measures. Current research lacks comprehensive investigations into safety incidents, relying heavily on conventional statistical methods and overlooking valuable textual information in publicly available databases. This study leverages a state-of-the-art large language model (LLM), specifically OpenAI’s GPT-3.5 model. The primary focus is to enhance text-based incident analysis that is sourced from OSHA’s Severe Injury Reports (SIR) database. By incorporating novel natural language processing (NLP) techniques, dimensionality reduction, clustering algorithms, and LLM prompting of incident narratives, the study aims to develop an approach to the analysis of major accident causes in highway construction. The resulting cluster analysis, coupled with LLM summarization and cause identification, reveals the major accident types, such as heat-related and struck-by injuries, as well as commonalities between incidents. This research showcases the potential of artificial intelligence (AI) and LLM technology in data-driven analysis. By efficiently processing textual data and providing insightful analysis, the study fosters practical implications for safety professionals and the development of more effective accident prevention and intervention strategies within the industry.
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
“A key limitation addressed by the authors is the need for domain-specific tuning to address knowledge gaps in construction safety and accurately identify and consider site-specific details.”
From A review of LLMs and their applications in the architecture, engineering and construction industry (2025) · cites this paper as Smetana et al. (2024)
Citations
Cites
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reimers, N., & Gurevych, I. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1410 · Cited by 12,778
Harris, Z. S. (1954) · WORD · doi:10.1080/00437956.1954.11659520 · Cited by 4,807
Topic Modeling in Embedding Spaces
Dieng, A. B., Ruiz, F. J. R., & Blei, D. M. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00325 · Cited by 780
MTEB: Massive Text Embedding Benchmark
Muennighoff, N., Tazi, N., Magne, L., & Reimers, N. (2023) · Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.148 · Cited by 548
Construction accident narrative classification: An evaluation of text mining techniques
Goh, Y. M., & Ubeynarayana, C. U. (2017) · Accident Analysis & Prevention · doi:10.1016/j.aap.2017.08.026 · Cited by 273
Investigating the Use of ChatGPT for the Scheduling of Construction Projects
Prieto, S. A., Mengiste, E. T., & García de Soto, B. (2023) · Buildings · doi:10.3390/buildings13040857 · Cited by 229
GPT models in construction industry: Opportunities, limitations, and a use case validation
Saka, A., Taiwo, R., Saka, N., Salami, B. A., Ajayi, S., Akande, K., & Kazemi, H. (2024) · Developments in the Built Environment · doi:10.1016/j.dibe.2023.100300 · Cited by 202
Automated text classification of near-misses from safety reports: An improved deep learning approach
Fang, W., Luo, H., Xu, S., Love, P. E. D., Lu, Z., & Ye, C. (2020) · Advanced Engineering Informatics · doi:10.1016/j.aei.2020.101060 · Cited by 198
Ma, Z., Mei, G., & Cuomo, S. (2021) · Accident Analysis & Prevention · doi:10.1016/j.aap.2021.106322 · Cited by 184
The Nature of Struck-by Accidents
Hinze, J., Huang, X., & Terry, L. (2005) · Journal of Construction Engineering and Management · doi:10.1061/(asce)0733-9364(2005)131:2(262 · Cited by 158
Research works printed but not linked: 5
- Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., and Fedus, W. (2022). Emergent Abilities of Large Language Models. arXiv.
- Neelakantan, A., Xu, T., Puri, R., Radford, A., Han, J.M., Tworek, J., and Weng, L. (2022). Text and Code Embeddings by Contrastive Pre-Training. arXiv.
- Hinton, 2008, Viualizing data using t-SNE, J. Mach. Learn. Res., 9, 2579
- Radford, A., Narasimhan, K., Salimans, T., and Sutskever, I. (2023, July 17). Improving Language Understanding by Generative Pre-Training. Available online: https://api.semanticscholar.org/CorpusID:49313245.
- Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., and Sutskever, I. (2023, July 17). Language Models Are Unsupervised Multitask Learners. Available online: https://api.semanticscholar.org/CorpusID:16002553.
Cited by
Onatayo, D. A., Onososen, A. O., Oyediran, A. O., Oyediran, H., Arowoiya, V. A., & Onatayo, E. (2024) · Architecture · doi:10.3390/architecture4040046 · Cited by 174
Chengke, W., Ding, W., Jin, Q., Jiang, J., Jiang, R., Xiao, Q., Liao, L., & Li, X. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103158 · Cited by 120
A review of LLMs and their applications in the architecture, engineering and construction industry
Kampelopoulos, D., Tsanousa, A., Vrochidis, S., & Kompatsiaris, I. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11241-7 · Cited by 69
Applications of multimodal large language models in construction industry
Erfani, A., & Mansouri, A. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103909 · Cited by 61
GeoLLM: A specialized large language model framework for intelligent geotechnical design
Xu, H., Zhang, N., Yin, Z., & Njock, P. G. A. (2024) · Computers and Geotechnics · doi:10.1016/j.compgeo.2024.106849 · Cited by 52
Metadata
- Authors
- Smetana, M., Salles de Salles, L., Sukharev, I., & Khazanovich, L.
- Affiliations
- University of Pittsburgh (US)
- Department of Civil Engineering Technology, Environmental Management and Safety, Rochester Institute of Technology, Rochester, NY 14623, USA
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2024-02-06
- Volume
- 14
- Issue
- 4
- Pages
- 1352
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W4391614156
- Cited by
- 87
- References
- 38
- Citations by year
- 2026: 43 · 2025: 39 · 2024: 5
- FWCI
- 34.95
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- University of Pittsburgh Anthony Gill Chair (PITTIRISE2018)
- Impactful Resilient Infrastructure Science & Engineering (IRISE) Consortium (PITTIRISE2018)
- Topics
- Social Sciences › Safety Research › Occupational Health and Safety Research
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Traffic and Road Safety
- Health Sciences › Health Professions › Occupational Therapy › Occupational Health and Safety Management
- Keywords
- highway construction safety, occupational injuries, large language models, GPT-3.5, accident cause identification, heat injury, accident prevention
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: Highway Construction Safety Analysis Using Large Language Models. https://app.cochat.ai/papers/10.3390/app14041352
- The paper
- Smetana, M., Salles de Salles, L., Sukharev, I., & Khazanovich, L. (2024). Highway Construction Safety Analysis Using Large Language Models. Applied Sciences. https://doi.org/10.3390/app14041352
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.