{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T11:10:34Z","timestamp":1776078634502,"version":"3.50.1"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T00:00:00Z","timestamp":1775433600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100019779","name":"Qatar National Library","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019779","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Advanced Engineering Informatics"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.aei.2026.104679","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T09:39:31Z","timestamp":1775641171000},"page":"104679","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["An agentic framework for data augmentation in construction defect report classification"],"prefix":"10.1016","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3703-0836","authenticated-orcid":false,"given":"Uzair","family":"Ahmad","sequence":"first","affiliation":[]},{"given":"Hasan","family":"Haroglu","sequence":"additional","affiliation":[]},{"given":"Algan","family":"Tezel","sequence":"additional","affiliation":[]},{"given":"Bekir Sait","family":"Ciftler","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.aei.2026.104679_b1","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1080\/014461999371420","article-title":"Determining the causal structure of rework influences in construction","volume":"17","author":"Love","year":"1999","journal-title":"Constr. Manag. Econ."},{"issue":"2","key":"10.1016\/j.aei.2026.104679_b2","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1108\/CI-10-2022-0254","article-title":"Development of building defects dashboards and stochastic models for multi-storey buildings in victoria, australia","volume":"25","author":"Gurmu","year":"2025","journal-title":"Constr. Innov."},{"key":"10.1016\/j.aei.2026.104679_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2022.104543","article-title":"Named entity recognition of building construction defect information from text with linguistic noise","volume":"143","author":"Jeon","year":"2022","journal-title":"Autom. Constr."},{"key":"10.1016\/j.aei.2026.104679_b4","article-title":"Interpretable machine learning-based text classification method for construction quality defect reports","volume":"89","author":"Wang","year":"2024","journal-title":"J. Build. Eng."},{"issue":"9","key":"10.1016\/j.aei.2026.104679_b5","doi-asserted-by":"crossref","DOI":"10.1061\/(ASCE)CO.1943-7862.0001897","article-title":"Defect risk assessment using a hybrid machine learning method","volume":"146","author":"Fan","year":"2020","journal-title":"J. Constr. Eng. Manag."},{"key":"10.1016\/j.aei.2026.104679_b6","article-title":"Text mining and natural language processing in construction","volume":"118","author":"Shamshiri","year":"2020","journal-title":"Autom. Constr."},{"key":"10.1016\/j.aei.2026.104679_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2021.103915","article-title":"A critical review of text-based research in construction: Data source, analysis method, and implications","volume":"132","author":"Baek","year":"2021","journal-title":"Autom. Constr."},{"issue":"7","key":"10.1016\/j.aei.2026.104679_b8","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1108\/CI-04-2024-0123","article-title":"Clustering techniques and keyword extraction with large language models for knowledge discovery in building defects data","volume":"25","author":"Cusumano","year":"2025","journal-title":"Constr. Innov."},{"key":"10.1016\/j.aei.2026.104679_b9","doi-asserted-by":"crossref","first-page":"7143","DOI":"10.1016\/j.eswa.2010.12.047","article-title":"Integrating data mining with kj method to classify bridge construction defects","volume":"38","author":"Cheng","year":"2011","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.aei.2026.104679_b10","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.autcon.2014.12.016","article-title":"Ga-based multi-level association rule mining approach for defect analysis in the construction industry","volume":"51","author":"Cheng","year":"2015","journal-title":"Autom. Constr."},{"key":"10.1016\/j.aei.2026.104679_b11","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.aei.2019.02.009","article-title":"Convolutional neural network: Deep learning-based classification of building quality problems","volume":"40","author":"Zhong","year":"2019","journal-title":"Adv. Eng. Inform."},{"issue":"10","key":"10.1016\/j.aei.2026.104679_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.asej.2024.102983","article-title":"Intelligent classification of construction quality problems based on unbalanced short text data mining","volume":"15","author":"Wang","year":"2024","journal-title":"Ain Shams Eng. J."},{"key":"10.1016\/j.aei.2026.104679_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2021.103821","article-title":"An engineer\u2019s guide to explainable artificial intelligence and interpretable machine learning: Navigating causality, forced goodness, and the false perception of inference","volume":"129","author":"Naser","year":"2021","journal-title":"Autom. Constr."},{"key":"10.1016\/j.aei.2026.104679_b14","article-title":"An interpretable machine learning approach for evaluating the feature importance affecting lost workdays at construction sites","volume":"53","author":"Kang","year":"2022","journal-title":"J. Build. Eng."},{"key":"10.1016\/j.aei.2026.104679_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.scs.2022.103803","article-title":"Autodefect: Defect text classification in residential buildings using a multi-task channel attention network","volume":"80","author":"Yang","year":"2022","journal-title":"Sustain. Cities Soc."},{"key":"10.1016\/j.aei.2026.104679_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2021.101355","article-title":"On-site text classification and knowledge mining for large-scale projects construction by integrated intelligent approach","volume":"49","author":"Tian","year":"2021","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.aei.2026.104679_b17","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.autcon.2016.05.016","article-title":"Application of machine learning to construction injury prediction","volume":"69","author":"Tixier","year":"2016","journal-title":"Autom. Constr."},{"key":"10.1016\/j.aei.2026.104679_b18","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. Constr."},{"key":"10.1016\/j.aei.2026.104679_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2020.103265","article-title":"Text mining-based construction site accident classification using hybrid supervised machine learning","volume":"118","author":"Cheng","year":"2020","journal-title":"Autom. Constr."},{"key":"10.1016\/j.aei.2026.104679_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2021.101256","article-title":"A small samples training framework for deep learning-based automatic information extraction: Case study of construction accident news reports analysis","volume":"47","author":"Feng","year":"2021","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.aei.2026.104679_b21","article-title":"Deep learning and text mining: Classifying and extracting key information from construction accident narratives","volume":"13","author":"e. a. Goh","year":"2023","journal-title":"Appl. Sci."},{"key":"10.1016\/j.aei.2026.104679_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2024.105343","article-title":"Mining construction accident reports via unsupervised nlp and accimap for systemic risk analysis","volume":"161","author":"Ma","year":"2024","journal-title":"Autom. Constr."},{"issue":"4","key":"10.1016\/j.aei.2026.104679_b23","doi-asserted-by":"crossref","DOI":"10.1061\/(ASCE)LA.1943-4170.0000308","article-title":"Application of natural language processing and text mining to identify patterns in construction-defect litigation cases","volume":"11","author":"Jallan","year":"2019","journal-title":"J. Leg. Aff. Disput. Resolut. Eng. Constr."},{"issue":"2","key":"10.1016\/j.aei.2026.104679_b24","article-title":"Developing and evaluating a classification model for construction defect control: A text mining and ensemble learning approach","volume":"41","author":"Jo","year":"2025","journal-title":"J. Manag. Eng."},{"key":"10.1016\/j.aei.2026.104679_b25","article-title":"Expert annotation costs and quality trade-offs in construction defect documentation","volume":"145","author":"L\u00f3pez","year":"2023","journal-title":"Autom. Constr."},{"key":"10.1016\/j.aei.2026.104679_b26","series-title":"Proceedings of China National Conference on Chinese Computational Linguistics","first-page":"194","article-title":"How to fine-tune BERT for text classification?","author":"Sun","year":"2019"},{"key":"10.1016\/j.aei.2026.104679_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2024.105316","article-title":"Domain-specific language models pre-trained on construction management systems corpora","volume":"160","author":"Zhong","year":"2024","journal-title":"Autom. Constr."},{"key":"10.1016\/j.aei.2026.104679_b28","series-title":"ISARC. Proceedings of the International Symposium on Automation and Robotics in Construction","first-page":"238","article-title":"Prospects of integrating bim and nlp for automatic construction schedule management","volume":"Vol. 40","author":"Singh","year":"2023"},{"key":"10.1016\/j.aei.2026.104679_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.autcon.2024.105443","article-title":"Ai integration in construction safety: Current state, challenges, and future opportunities in text, vision, and audio based applications","volume":"164","author":"Rabbi","year":"2024","journal-title":"Autom. Constr."},{"key":"10.1016\/j.aei.2026.104679_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102606","article-title":"Generating synthetic data with variational autoencoder to address class imbalance of graph attention network prediction model for construction management","volume":"62","author":"Mostofi","year":"2024","journal-title":"Adv. Eng. Informatics"},{"key":"10.1016\/j.aei.2026.104679_b31","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"Smote: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artificial Intelligence Res."},{"key":"10.1016\/j.aei.2026.104679_b32","series-title":"Proceedings of EMNLP-IJCNLP","article-title":"Eda: Easy data augmentation techniques for boosting performance on text classification tasks","author":"Wei","year":"2019"},{"key":"10.1016\/j.aei.2026.104679_b33","series-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"86","article-title":"Improving neural machine translation models with monolingual data","author":"Sennrich","year":"2016"},{"key":"10.1016\/j.aei.2026.104679_b34","series-title":"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"10476","article-title":"LLMs vs established text augmentation techniques for classification: When do the benefits outweight the costs?","author":"Cegin","year":"2025"},{"key":"10.1016\/j.aei.2026.104679_b35","series-title":"Contextual augmentation: Data augmentation by words with paradigmatic relations","author":"Kobayashi","year":"2018"},{"key":"10.1016\/j.aei.2026.104679_b36","series-title":"Proceedings of the 37th International Conference on Machine Learning","first-page":"11392","article-title":"PEGASUS: Pre-training with extracted gap-sentences for abstractive summarization","volume":"vol. 119","author":"Zhang","year":"2020"},{"issue":"1","key":"10.1016\/j.aei.2026.104679_b37","doi-asserted-by":"crossref","first-page":"148","DOI":"10.47839\/ijc.24.1.3886","article-title":"Using large language models for data augmentation in text classification models","volume":"24","author":"Pavlyshenko","year":"2025","journal-title":"Int. J. Comput."},{"issue":"9","key":"10.1016\/j.aei.2026.104679_b38","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"5","key":"10.1016\/j.aei.2026.104679_b39","doi-asserted-by":"crossref","first-page":"429","DOI":"10.3233\/IDA-2002-6504","article-title":"The class imbalance problem: A systematic study","volume":"6","author":"Japkowicz","year":"2002","journal-title":"Intell. Data Anal."},{"issue":"5","key":"10.1016\/j.aei.2026.104679_b40","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","article-title":"Term-weighting approaches in automatic text retrieval","volume":"24","author":"Salton","year":"1988","journal-title":"Inf. Process. Manage."},{"key":"10.1016\/j.aei.2026.104679_b41","series-title":"Dynamic Programming","author":"Bellman","year":"1966"},{"key":"10.1016\/j.aei.2026.104679_b42","series-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing","first-page":"3982","article-title":"Sentence-bert: Sentence embeddings using siamese bert-networks","author":"Reimers","year":"2019"},{"key":"10.1016\/j.aei.2026.104679_b43","series-title":"Thirty-Fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","first-page":"1","article-title":"Beir: A heterogeneous benchmark for zero-shot evaluation of information retrieval models","author":"Thakur","year":"2021"},{"key":"10.1016\/j.aei.2026.104679_b44","series-title":"NeurIPS","first-page":"1877","article-title":"Language models are few-shot learners","volume":"Vol. 33","author":"Brown","year":"2020"},{"issue":"1","key":"10.1016\/j.aei.2026.104679_b45","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"issue":"3","key":"10.1016\/j.aei.2026.104679_b46","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"10.1016\/j.aei.2026.104679_b47","doi-asserted-by":"crossref","unstructured":"T. Chen, C. Guestrin, Xgboost: A scalable tree boosting system, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"10.1016\/j.aei.2026.104679_b48","series-title":"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)","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"10.1016\/j.aei.2026.104679_b49","series-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"issue":"4","key":"10.1016\/j.aei.2026.104679_b50","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1162\/coli.07-034-R2","article-title":"Inter-coder agreement for computational linguistics","volume":"34","author":"Artstein","year":"2008","journal-title":"Comput. Linguist."},{"key":"10.1016\/j.aei.2026.104679_b51","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.jbi.2017.11.011","article-title":"Clinical information extraction applications: a literature review","volume":"77","author":"Wang","year":"2018","journal-title":"J. Biomed. Inform."},{"key":"10.1016\/j.aei.2026.104679_b52","author":"of Chartered Surveyors","year":"2023"},{"key":"10.1016\/j.aei.2026.104679_b53","series-title":"Active Learning Literature Survey","author":"Settles","year":"2009"}],"container-title":["Advanced Engineering Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S147403462600371X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S147403462600371X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T10:25:17Z","timestamp":1776075917000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S147403462600371X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":53,"alternative-id":["S147403462600371X"],"URL":"https:\/\/doi.org\/10.1016\/j.aei.2026.104679","relation":{},"ISSN":["1474-0346"],"issn-type":[{"value":"1474-0346","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An agentic framework for data augmentation in construction defect report classification","name":"articletitle","label":"Article Title"},{"value":"Advanced Engineering Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.aei.2026.104679","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":"104679"}}