{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T06:10:11Z","timestamp":1778566211832,"version":"3.51.4"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100007921","name":"University of Pittsburgh","doi-asserted-by":"publisher","award":["PITTIRISE2018"],"award-info":[{"award-number":["PITTIRISE2018"]}],"id":[{"id":"10.13039\/100007921","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.engappai.2026.114798","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T17:58:26Z","timestamp":1775757506000},"page":"114798","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P2","title":["Improving large language model assisted categorization and classification of highway construction accidents"],"prefix":"10.1016","volume":"176","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4130-3781","authenticated-orcid":false,"given":"Mason","family":"Smetana","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9080-4448","authenticated-orcid":false,"given":"Lucio","family":"Salles de Salles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lev","family":"Khazanovich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.114798_bib1","series-title":"Proceedings of the 11th Annual Meeting of the Forum for Information Retrieval (FIRE \u201910)","first-page":"24","article-title":"Authorship clustering using TF-IDF weighted word-embeddings","author":"Agarwal","year":"2019"},{"key":"10.1016\/j.engappai.2026.114798_bib2","series-title":"Proceedings of the 8th International Conference on Advanced Informatics Concepts, Theory and Applications (ICAICTA)","first-page":"1","article-title":"Improving the performance of HDBSCAN on short text clustering by using word embedding and UMAP","author":"Asyaky","year":"2021"},{"issue":"3","key":"10.1016\/j.engappai.2026.114798_bib3","doi-asserted-by":"crossref","DOI":"10.1061\/(ASCE)CO.1943-7862.0001762","article-title":"Accident analysis for construction safety using latent class clustering and artificial neural networks","volume":"146","author":"Ayhan","year":"2020","journal-title":"J. Construct. Eng. Manag."},{"key":"10.1016\/j.engappai.2026.114798_bib4","article-title":"Few-shot text classification with pre-trained word embeddings and a human in the loop","author":"Bailey","year":"2018","journal-title":"arXiv preprint"},{"key":"10.1016\/j.engappai.2026.114798_bib5","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2020.103145","article-title":"Automatically learning construction injury precursors from text","volume":"118","author":"Baker","year":"2020","journal-title":"Autom. ConStruct."},{"issue":"1","key":"10.1016\/j.engappai.2026.114798_bib6","first-page":"53","article-title":"Beyond the curse of multidimensionality: high dimensional clustering in text mining","volume":"22","author":"Balbi","year":"2010","journal-title":"Statistica Appl. - Italian J. Appl. Statist."},{"issue":"3","key":"10.1016\/j.engappai.2026.114798_bib7","doi-asserted-by":"crossref","DOI":"10.1061\/JCCEE5.CPENG-4868","article-title":"Developing a construction domain\u2013specific artificial intelligence language model for NCDOT's CLEAR program to promote organizational innovation and institutional knowledge","volume":"37","author":"Banerjee","year":"2023","journal-title":"J. Comput. Civ. Eng."},{"key":"10.1016\/j.engappai.2026.114798_bib8","series-title":"Proceedings of the 34th Conference on Neural Information Processing Systems (NeurIPS 2020)","first-page":"1877","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"10.1016\/j.engappai.2026.114798_bib9","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2021.104215","article-title":"Using modified term frequency to improve term weighting for text classification","volume":"101","author":"Chen","year":"2021","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114798_bib10","doi-asserted-by":"crossref","first-page":"1588","DOI":"10.1016\/j.proeng.2016.04.200","article-title":"Analyzing Arizona OSHA injury reports using unsupervised machine learning","volume":"145","author":"Chokor","year":"2016","journal-title":"Procedia Eng."},{"key":"10.1016\/j.engappai.2026.114798_bib11","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112164","article-title":"Accidents analysis of mining industry through semantic text representation and dimensionality reduction: an integrated clustering framework","volume":"161","author":"Danish","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"1","key":"10.1016\/j.engappai.2026.114798_bib12","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/1327452.1327492","article-title":"MapReduce: simplified data processing on large clusters","volume":"51","author":"Dean","year":"2008","journal-title":"Commun. ACM"},{"key":"10.1016\/j.engappai.2026.114798_bib13","doi-asserted-by":"crossref","first-page":"180171","DOI":"10.1109\/ACCESS.2020.3028235","article-title":"Hazardous chemical accident prevention based on K-Means clustering analysis of incident information","volume":"8","author":"Deng","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114798_bib14","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/j.cie.2018.12.044","article-title":"Decision support system for safety improvement: an approach using multiple correspondence analysis, t-SNE algorithm and K-means clustering","volume":"128","author":"Dhalmahapatra","year":"2019","journal-title":"Comput. Ind. Eng."},{"key":"10.1016\/j.engappai.2026.114798_bib15","series-title":"Proceedings of the 39th International Symposium on Automation and Robotics in Construction (ISARC 2022)","first-page":"653","article-title":"Action sequencing in construction accident reports using probabilistic language model","author":"Do","year":"2022"},{"key":"10.1016\/j.engappai.2026.114798_bib16","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2020.101060","article-title":"Automated text classification of near-misses from safety reports: an improved deep learning approach","volume":"44","author":"Fang","year":"2020","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.engappai.2026.114798_bib17","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.psep.2021.09.001","article-title":"Application of natural language processing in HAZOP reports","volume":"155","author":"Feng","year":"2021","journal-title":"Process Saf. Environ. Prot."},{"key":"10.1016\/j.engappai.2026.114798_bib18","series-title":"Proceedings of the 17th IEEE International Conference on Machine Learning and Applications (ICMLA 2018)","first-page":"1446","article-title":"Analysis of railway accidents' narratives using deep learning","author":"Heidarysafa","year":"2018"},{"key":"10.1016\/j.engappai.2026.114798_bib19","series-title":"Proceedings of the 36th Conference on Neural Information Processing (Neurips 2022)","article-title":"Large language models are zero-shot reasoners","author":"Kojima","year":"2023"},{"issue":"2","key":"10.1016\/j.engappai.2026.114798_bib20","doi-asserted-by":"crossref","first-page":"377","DOI":"10.3390\/buildings13020377","article-title":"Automatic construction hazard identification integrating On-Site scene graphs with information extraction in outfield test","volume":"13","author":"Liu","year":"2023","journal-title":"Buildings"},{"key":"10.1016\/j.engappai.2026.114798_bib21","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2021.102096","article-title":"Evaluation of clustering and topic modeling methods over health-related tweets and emails","volume":"117","author":"Lossio-Ventura","year":"2021","journal-title":"Artif. Intell. Med."},{"issue":"12","key":"10.1016\/j.engappai.2026.114798_bib22","doi-asserted-by":"crossref","DOI":"10.1061\/JCEMD4.COENG-13523","article-title":"Convolutional neural network algorithm\u2013based novel automatic text classification framework for construction accident reports","volume":"149","author":"Luo","year":"2023","journal-title":"J. Construct. Eng. Manag."},{"key":"10.1016\/j.engappai.2026.114798_bib23","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"9004","article-title":"SelfCheckGPT: zero-resource black-box hallucination detection for generative large language models","author":"Manakul","year":"2023"},{"key":"10.1016\/j.engappai.2026.114798_bib24","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2021.106322","article-title":"An analytic framework using deep learning for prediction of traffic accident injury severity based on contributing factors","volume":"160","author":"Ma","year":"2021","journal-title":"Accid. Anal. Prev."},{"key":"10.1016\/j.engappai.2026.114798_bib25","series-title":"Proceedings of the 17th Conference on the European Chapter of the Association for Computational Linguistics (EACL)","first-page":"2014","article-title":"MTEB: massive text embedding benchmark","author":"Muennighoff","year":"2023"},{"key":"10.1016\/j.engappai.2026.114798_bib26","article-title":"Text and code embeddings by contrastive pre-training","author":"Neelakantan","year":"2022","journal-title":"arXiv preprint"},{"issue":"6","key":"10.1016\/j.engappai.2026.114798_bib27","doi-asserted-by":"crossref","first-page":"770","DOI":"10.3390\/min13060770","article-title":"Contextual representation in NLP to improve success in accident classification of mine safety narratives","volume":"13","author":"Pothina","year":"2023","journal-title":"Minerals"},{"issue":"4","key":"10.1016\/j.engappai.2026.114798_bib28","doi-asserted-by":"crossref","first-page":"857","DOI":"10.3390\/buildings13040857","article-title":"Investigating the use of ChatGPT for the scheduling of construction projects","volume":"13","author":"Prieto","year":"2023","journal-title":"Buildings"},{"key":"10.1016\/j.engappai.2026.114798_bib29","series-title":"Proceedings of the Aisa-Pacific Conference on Image Processing, Electronics, and Computers (IPEC)","first-page":"47","article-title":"Research on micro-blog text presentation model based on Word2vec and TF-IDF","author":"Qiu","year":"2021"},{"key":"10.1016\/j.engappai.2026.114798_bib30","author":"Radford"},{"key":"10.1016\/j.engappai.2026.114798_bib31","series-title":"Language Models Are Unsupervised Multitask Learners","author":"Radford","year":"2019"},{"key":"10.1016\/j.engappai.2026.114798_bib32","doi-asserted-by":"crossref","first-page":"166603","DOI":"10.1109\/ACCESS.2021.3135662","article-title":"A novel implementation of an AI-Based smart construction safety inspection protocol in the UAE","volume":"9","author":"Shanti","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114798_bib33","article-title":"Enhancing occupational safety in construction: predictive analytics using advanced ensemble machine learning algorithms","volume":"149","author":"Shehadeh","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"1","key":"10.1016\/j.engappai.2026.114798_bib34","article-title":"A novel approach for dimension reduction using word embedding: an enhanced text classification approach","volume":"2","author":"Singh","year":"2022","journal-title":"Int. J. Inf. Manag. Data Insights"},{"issue":"4","key":"10.1016\/j.engappai.2026.114798_bib35","doi-asserted-by":"crossref","first-page":"1352","DOI":"10.3390\/app14041352","article-title":"Highway construction safety analysis using large language models","volume":"14","author":"Smetana","year":"2024","journal-title":"Appl. Sci."},{"key":"10.1016\/j.engappai.2026.114798_bib36","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2022.104670","article-title":"Intelligent question answering method for construction safety hazard knowledge based on deep semantic mining","volume":"145","author":"Tian","year":"2023","journal-title":"Autom. ConStruct."},{"key":"10.1016\/j.engappai.2026.114798_bib37","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.105742","article-title":"Intelligent mining of safety hazard information from construction documents using semantic similarity and information entropy","volume":"119","author":"Tian","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.114798_bib38","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.118157","article-title":"Word embedding dimensionality reduction using dynamic variance thresholding (DyVaT)","volume":"208","author":"Treistman","year":"2022","journal-title":"Expert Syst. Appl."},{"issue":"9","key":"10.1016\/j.engappai.2026.114798_bib39","doi-asserted-by":"crossref","first-page":"7121","DOI":"10.3390\/su15097121","article-title":"Leveraging ChatGPT to aid construction hazard recognition and support safety education and training","volume":"15","author":"Uddin","year":"2023","journal-title":"Sustainability"},{"issue":"2","key":"10.1016\/j.engappai.2026.114798_bib40","article-title":"Document similarity detection using K-Means and cosine distance","volume":"10","author":"Usino","year":"2019","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"issue":"86","key":"10.1016\/j.engappai.2026.114798_bib41","first-page":"2579","article-title":"Viualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.engappai.2026.114798_bib42","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.psep.2021.11.004","article-title":"Automatic frequency estimation of contributory factors for confined space accidents","volume":"157","author":"Wang","year":"2022","journal-title":"Process Saf. Environ. Prot."},{"key":"10.1016\/j.engappai.2026.114798_bib43","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"arXiv preprint"},{"key":"10.1016\/j.engappai.2026.114798_bib44","series-title":"Proceedings of the 36th Conference on Neural Information Processing (Neurips 2022)","first-page":"24824","article-title":"Chain-of-Thought prompting elicits reasoning in large language models","author":"Wei","year":"2023"},{"issue":"21","key":"10.1016\/j.engappai.2026.114798_bib45","doi-asserted-by":"crossref","DOI":"10.3390\/app122111220","article-title":"Identification and visualization of key topics in scientific publications with transformer-based language models and document clustering methods","volume":"12","author":"Weng","year":"2022","journal-title":"Appl. Sci."},{"issue":"1","key":"10.1016\/j.engappai.2026.114798_bib46","first-page":"1","article-title":"Word embeddings and semantic spaces in natural language processing","volume":"13","author":"Worth","year":"2023","journal-title":"Int. J. Intell. Sci."},{"issue":"9","key":"10.1016\/j.engappai.2026.114798_bib47","doi-asserted-by":"crossref","first-page":"1576","DOI":"10.1007\/s42452-020-3125-1","article-title":"Road accident prediction and model interpretation using a hybrid K-means and random forest algorithm approach","volume":"2","author":"Yassin","year":"2020","journal-title":"SN Appl. Sci."},{"key":"10.1016\/j.engappai.2026.114798_bib48","doi-asserted-by":"crossref","first-page":"30692","DOI":"10.1109\/ACCESS.2020.2973207","article-title":"Topic modeling for short texts via word embedding and document correlation","volume":"8","author":"Yi","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.engappai.2026.114798_bib50","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.autcon.2018.12.016","article-title":"Construction site accident analysis using text mining and natural language processing techniques","volume":"99","author":"Zhang","year":"2019","journal-title":"Autom. ConStruct."},{"key":"10.1016\/j.engappai.2026.114798_bib51","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109104","article-title":"Advanced informatic technologies for intelligent construction: a review","volume":"137","author":"Zhang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"5","key":"10.1016\/j.engappai.2026.114798_bib52","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.3390\/buildings13051169","article-title":"Discovering the research topics on construction safety and health using semi-supervised topic modeling","volume":"13","author":"Zhou","year":"2023","journal-title":"Buildings"},{"key":"10.1016\/j.engappai.2026.114798_bib53","article-title":"Large language models are human-level prompt engineers","author":"Zhou","year":"2023","journal-title":"arXiv preprint"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626010808?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626010808?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T05:14:13Z","timestamp":1778562853000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626010808"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":52,"alternative-id":["S0952197626010808"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114798","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Improving large language model assisted categorization and classification of highway construction accidents","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.114798","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"114798"}}