{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T04:31:05Z","timestamp":1771907465322,"version":"3.50.1"},"reference-count":15,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T00:00:00Z","timestamp":1706054400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>The present study explores and investigates the efficiency of deep learning models in identifying discourse structure and functional features and explores the potential application of natural language processing (NLP) techniques in text mining, information measurement, and scientific communication.<\/jats:p><\/jats:sec><jats:sec><jats:title>Method<\/jats:title><jats:p>The PLOS literature series has been utilized to obtain full-text data, and four deep learning models, including BERT, RoBERTa, SciBERT, and SsciBERT, have been employed for structure-function recognition.<\/jats:p><\/jats:sec><jats:sec><jats:title>Result<\/jats:title><jats:p>The experimental findings reveal that the SciBERT model performs outstandingly, surpassing the other models, with an F1 score. Additionally, the performance of different paragraph structures has been analyzed, and it has been found that the model performs well in paragraphs such as method and result.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The study's outcomes suggest that deep learning models can recognize the structure and functional elements at the discourse level, particularly for scientific literature, where the SciBERT model performs remarkably. Moreover, the NLP techniques have extensive prospects in various fields, including text mining, information measurement, and scientific communication. By automatically parsing and identifying structural and functional information in text, the efficiency of literature management and retrieval can be improved, thereby expediting scientific research progress. Therefore, deep learning and NLP technologies hold significant value in scientific research.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2024.1254671","type":"journal-article","created":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T04:39:38Z","timestamp":1706071178000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Research on the structure function recognition of PLOS"],"prefix":"10.3389","volume":"7","author":[{"given":"Jiangfeng","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhixiao","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2024,1,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"3174","DOI":"10.1093\/bioinformatics\/btp548","article-title":"Automatically classifying sentences in full-text biomedical articles into introduction, methods, results and discussion","volume":"25","author":"Agarwal","year":"2009","journal-title":"Bioinformatics"},{"key":"B2","doi-asserted-by":"crossref","unstructured":"BeltagyI.\n            LoK.\n            CohanA.\n          SciBERT: A pretrained language model for scientific text2019","DOI":"10.18653\/v1\/D19-1371"},{"key":"B3","unstructured":"DevlinJ.\n            ChangM. W.\n            LeeK.\n            ToutanovaK.\n          Bert: Pre-training of deep bidirectional transformers for language understanding2018"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.14236\/ewic\/IR1997.2","article-title":"Text-level structure of research papers: Implications for text-based information processing systems","volume":"19","author":"Kando","year":"1997","journal-title":"Proc. Ann. BCS-IRSG Colloquium IR Res."},{"key":"B5","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1016\/j.esp.2004.08.003","article-title":"Rhetorical structure of biochemistry research articles","volume":"24","author":"Kanoksilapatham","year":"2005","journal-title":"Eng. Specific Purp."},{"key":"B6","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3969\/j.issn.1008-0821.2019.12.007","article-title":"Multi-disciplinary comparative study on methods of academic text structure function recognition based on deep learning model","volume":"39","author":"Li","year":"2019","journal-title":"Modern Inf."},{"key":"B7","unstructured":"LiuY.\n            OttM.\n            GoyalN.\n            DuJ.\n            JoshiM.\n            ChenD.\n          Roberta: A robustly optimized bert pretraining approach2019"},{"key":"B8","doi-asserted-by":"publisher","first-page":"979","DOI":"10.3772\/j.issn.1000-0135.2014.09.010","article-title":"The structure function of academic text and its classification","volume":"33","author":"Lu","year":"2014","journal-title":"J. China Soc. Sci. Tech. Inf."},{"key":"B9","doi-asserted-by":"publisher","first-page":"65","DOI":"10.2478\/dim-2020-0031","article-title":"Exploring significant characteristics and models for classification of structure function of academic documents","volume":"5","author":"Ma","year":"2021","journal-title":"Data Inf. Manage."},{"key":"B10","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1007\/s11192-021-04225-1","article-title":"Enhancing identification of structure function of academic articles using contextual information","volume":"127","author":"Ma","year":"2022","journal-title":"Scientometrics"},{"key":"B11","article-title":"\u201cCategorization of sentence types in medical abstracts,\u201d","volume-title":"AMIA Annual Symposium Proceedings","author":"McKnight","year":"2003"},{"key":"B12","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1016\/j.ijmedinf.2005.06.013","article-title":"Zone analysis in biology articles as a basis for information extraction","volume":"75","author":"Mizuta","year":"2006","journal-title":"Int. J. Med. Inf."},{"key":"B13","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/S0889-4906(98)00001-5","article-title":"The schematic structure of computer science research articles","volume":"18","author":"Posteguillo","year":"1999","journal-title":"Eng. Spec. Purp."},{"key":"B14","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1109\/ICBK.2018.00034","article-title":"\u201cDiscovering IMRaD structure with different classifiers,\u201d","volume-title":"2018 IEEE International Conference on Big Knowledge (ICBK)","author":"Ribeiro","year":"2018"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1007\/s11192-022-04602-4","article-title":"SsciBERT: a pre-trained language model for social science texts","volume":"128","author":"Shen","year":"2023","journal-title":"Scientometrics"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1254671\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T04:39:43Z","timestamp":1706071183000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1254671\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,24]]},"references-count":15,"alternative-id":["10.3389\/frai.2024.1254671"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1254671","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,24]]},"article-number":"1254671"}}