{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T05:29:00Z","timestamp":1786339740270,"version":"build-2736575974"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T00:00:00Z","timestamp":1707264000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T00:00:00Z","timestamp":1707264000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Research Foundation of Education Bureau of Hunan Province of China","award":["20B625"],"award-info":[{"award-number":["20B625"]}]},{"name":"Research Foundation of Education Bureau of Hunan Province of China","award":["18B196"],"award-info":[{"award-number":["18B196"]}]},{"name":"Research Foundation of Education Bureau of Hunan Province of China","award":["22B0275"],"award-info":[{"award-number":["22B0275"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61802444"],"award-info":[{"award-number":["61802444"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Local Community Structure Detection Algorithms in Complex Networks","award":["2020YJ009"],"award-info":[{"award-number":["2020YJ009"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1007\/s00500-023-09623-6","type":"journal-article","created":{"date-parts":[[2024,2,7]],"date-time":"2024-02-07T11:02:06Z","timestamp":1707303726000},"page":"5127-5140","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A two-stage entity event deduplication method based on graph node selection and node optimization strategy"],"prefix":"10.1007","volume":"30","author":[{"given":"Wei","family":"Ai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongen","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keqin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,7]]},"reference":[{"key":"9623_CR1","doi-asserted-by":"crossref","unstructured":"Ai W, Xu J, Shao H et al (2021) An entity event deduplication method based on connected subgraph. In: 2021 7th international conference on systems and informatics (ICSAI), IEEE, pp 1\u20136","DOI":"10.1109\/ICSAI53574.2021.9664040"},{"key":"9623_CR2","doi-asserted-by":"crossref","unstructured":"Arun P, Sumesh M (2015) Near-duplicate web page detection by enhanced TDW and simHash technique. In: 2015 international conference on computing and network communications (CoCoNet), IEEE, pp 765\u2013770","DOI":"10.1109\/CoCoNet.2015.7411276"},{"key":"9623_CR3","first-page":"96","volume":"7","author":"R Bodankar","year":"2020","unstructured":"Bodankar R, Waghmare M (2020) Int J Sci Res Sci Eng Technol. Identification and effective summary extraction with deduplication of data in news articles 7:96\u2013102","journal-title":"Identification and effective summary extraction with deduplication of data in news articles"},{"key":"9623_CR4","doi-asserted-by":"crossref","unstructured":"Broder AZ (1997) On the resemblance and containment of documents. In: Proceedings. compression and complexity of SEQUENCES 1997 (Cat. No. 97TB100171), IEEE, pp 21\u201329","DOI":"10.1109\/SEQUEN.1997.666900"},{"key":"9623_CR5","doi-asserted-by":"crossref","unstructured":"Charikar MS (2002) Similarity estimation techniques from rounding algorithms. In: Proceedings of the thirty-fourth annual ACM symposium on theory of computing, pp 380\u2013388","DOI":"10.1145\/509907.509965"},{"key":"9623_CR6","unstructured":"Chen Z (2010) Graph-based clustering and its application in coreference resolution. In: Proceedings of the 2010 workshop on graph-based methods for natural language processing, pp 1\u20139"},{"key":"9623_CR7","unstructured":"Devlin J, Chang MW, Lee K et al (2018) Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. pp 4171\u20134186"},{"key":"9623_CR8","doi-asserted-by":"crossref","unstructured":"Fedoryszak M, Frederick B, Rajaram V et al (2019) Real-time event detection on social data streams. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pp 2774\u20132782","DOI":"10.1145\/3292500.3330689"},{"key":"9623_CR9","doi-asserted-by":"crossref","unstructured":"Ge Y, Wu J, Dai G et al (2019) Text deduplication with minimum loss ratio. In: Proceedings of the 2019 11th international conference on machine learning and computing, pp 310\u2013316","DOI":"10.1145\/3318299.3318369"},{"key":"9623_CR10","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.elerap.2018.02.006","volume":"28","author":"S Han","year":"2018","unstructured":"Han S, Hao X, Huang H (2018) An event-extraction approach for business analysis from online Chinese news. Electron Commerc Res Appl 28:244\u2013260","journal-title":"Electron Commerc Res Appl"},{"issue":"1","key":"9623_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13278-020-00658-3","volume":"10","author":"AH Hossny","year":"2020","unstructured":"Hossny AH, Mitchell L, Lothian N et al (2020) Feature selection methods for event detection in twitter: a text mining approach. Soc Netw Anal Min 10(1):1\u201315","journal-title":"Soc Netw Anal Min"},{"key":"9623_CR12","doi-asserted-by":"crossref","unstructured":"Huang D, Hu S, Cai Y et al (2014) Discovering event evolution graphs based on news articles relationships. In: 2014 IEEE 11th international conference on e-business engineering, IEEE, pp 246\u2013251","DOI":"10.1109\/ICEBE.2014.49"},{"key":"9623_CR13","doi-asserted-by":"crossref","unstructured":"Jadhav A, Rajan V (2018) Extractive summarization with SWAP-NET: sentences and words from alternating pointer networks. In: Proceedings of the 56th annual meeting of the association for computational linguistics (volume 1: Long papers), pp 142\u2013151","DOI":"10.18653\/v1\/P18-1014"},{"key":"9623_CR14","doi-asserted-by":"crossref","unstructured":"Liu S, Liu K, He S et al (2016) A probabilistic soft logic based approach to exploiting latent and global information in event classification. In: Thirtieth AAAI conference on artificial intelligence, p 2993\u20132999","DOI":"10.1609\/aaai.v30i1.10375"},{"key":"9623_CR15","doi-asserted-by":"crossref","unstructured":"Liu B, Niu D, Wei H et al (2018) Matching article pairs with graphical decomposition and convolutions. arXiv preprint arXiv:1802.07459","DOI":"10.18653\/v1\/P19-1632"},{"key":"9623_CR16","doi-asserted-by":"crossref","unstructured":"Manku GS, Jain A, Das Sarma A (2007) Detecting near-duplicates for web crawling. In: Proceedings of the 16th international conference on World wide web, pp 141\u2013150","DOI":"10.1145\/1242572.1242592"},{"key":"9623_CR17","doi-asserted-by":"crossref","unstructured":"McConky K, Nagi R, Sudit M et al (2012) Improving event co-reference by context extraction and dynamic feature weighting. In: 2012 IEEE international multi-disciplinary conference on cognitive methods in situation awareness and decision support, IEEE, pp 38\u201343","DOI":"10.1109\/CogSIMA.2012.6188406"},{"key":"9623_CR18","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1016\/j.knosys.2016.07.032","volume":"110","author":"B Navarro-Colorado","year":"2016","unstructured":"Navarro-Colorado B, Saquete E (2016) Cross-document event ordering through temporal, lexical and distributional knowledge. Knowl Based Syst 110:244\u2013254","journal-title":"Knowl Based Syst"},{"key":"9623_CR19","doi-asserted-by":"crossref","unstructured":"Schinas M, Papadopoulos S, Petkos G et\u00a0al (2015) Multimodal graph-based event detection and summarization in social media streams. In: Proceedings of the 23rd ACM international conference on multimedia, pp 189\u2013192","DOI":"10.1145\/2733373.2809933"},{"key":"9623_CR20","doi-asserted-by":"crossref","unstructured":"Sharapova E, Sharapov R (2019) Detection of fuzzy duplicate texts in news feeds. 2019 systems of signal synchronization. Generating and processing in telecommunications (SYNCHROINFO), IEEE, pp 1\u20135","DOI":"10.1109\/SYNCHROINFO.2019.8814112"},{"key":"9623_CR21","unstructured":"Tomadaki E, Salway A (2005) Matching verb attributes for cross-document event co-reference. In: Proceedings of interdisciplinary workshop on the identification and representation of verb features and verb classes, pp 127\u2013132"},{"key":"9623_CR22","doi-asserted-by":"crossref","unstructured":"UzZaman N, Allen JF (2010) Extracting events and temporal expressions from text. In: 2010 IEEE fourth international conference on semantic computing, IEEE, pp 1\u20138","DOI":"10.1109\/ICSC.2010.45"},{"key":"9623_CR23","doi-asserted-by":"crossref","unstructured":"Wang X, Dong X, Chen S (2020) Text duplicated-checking algorithm implementation based on natural language semantic analysis. In: 2020 IEEE 5th information technology and mechatronics engineering conference (ITOEC), IEEE, pp 732\u2013735","DOI":"10.1109\/ITOEC49072.2020.9141886"},{"issue":"6684","key":"9623_CR24","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1038\/30918","volume":"393","author":"DJ Watts","year":"1998","unstructured":"Watts DJ, Strogatz SH (1998) Collective dynamics of \u2018small-world\u2019 networks. Nature 393(6684):440\u2013442","journal-title":"Nature"},{"issue":"4","key":"9623_CR25","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1109\/TSMCA.2009.2015885","volume":"39","author":"CC Yang","year":"2009","unstructured":"Yang CC, Shi X, Wei CP (2009) Discovering event evolution graphs from news corpora. IEEE Trans Syst Man Cybern Part A Syst Hum 39(4):850\u2013863","journal-title":"IEEE Trans Syst Man Cybern Part A Syst Hum"},{"key":"9623_CR26","first-page":"1","volume":"10","author":"X Zhang","year":"2016","unstructured":"Zhang X, Yao Y, Ji Y et al (2016) Effective and fast near duplicate detection via signature-based compression metrics. Math Probl Eng 10:1\u201312","journal-title":"Math Probl Eng"},{"key":"9623_CR27","doi-asserted-by":"crossref","unstructured":"Zhang X, Liu Z, Liu W et al (2011) Event similarity computation in text. In: 2011 International conference on internet of things and 4th international conference on cyber. Physical and social computing, IEEE, pp 419\u2013423","DOI":"10.1109\/iThings\/CPSCom.2011.60"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-023-09623-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00500-023-09623-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-023-09623-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T05:00:02Z","timestamp":1786338002000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00500-023-09623-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,7]]},"references-count":27,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["9623"],"URL":"https:\/\/doi.org\/10.1007\/s00500-023-09623-6","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,7]]},"assertion":[{"value":"28 December 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"All authors declare that he has no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Informed consent was obtained from all individual participants included in the study.","order":3,"name":"Ethics","label":"Informed consent","group":{"name":"EthicsHeading","label":"Declarations"}}]}}