{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T22:52:26Z","timestamp":1777330346501,"version":"3.51.4"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,7,13]],"date-time":"2018-07-13T00:00:00Z","timestamp":1531440000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,7,13]],"date-time":"2018-07-13T00:00:00Z","timestamp":1531440000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Evolving Systems"],"published-print":{"date-parts":[[2020,9]]},"DOI":"10.1007\/s12530-018-9232-1","type":"journal-article","created":{"date-parts":[[2018,7,13]],"date-time":"2018-07-13T14:56:14Z","timestamp":1531493774000},"page":"503-515","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["An efficient classification approach in imbalanced datasets for intrinsic plagiarism detection"],"prefix":"10.1007","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0715-4355","authenticated-orcid":false,"given":"Andrianna","family":"Polydouri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eleni","family":"Vathi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Siolas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Stafylopatis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,7,13]]},"reference":[{"key":"9232_CR1","doi-asserted-by":"publisher","unstructured":"Alsallal M, Iqbal R, Amin S, James A (2013) Intrinsic plagiarism detection using latent semantic indexing and stylometry. In: 2013 Sixth international conference on developments in eSystems engineering, Abu Dhabi, pp 145\u2013150. https:\/\/doi.org\/10.1109\/DeSE.2013.34","DOI":"10.1109\/DeSE.2013.34"},{"key":"9232_CR2","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1109\/TSMCC.2011.2134847","volume":"42","author":"S Alzahrani","year":"2012","unstructured":"Alzahrani S, Salim N, Abraham A (2012) Understanding plagiarism linguistic patterns, textual features, and detection methods. IEEE Trans Syst Man Cybern Part C (Applications and Reviews) 42:133\u2013149","journal-title":"IEEE Trans Syst Man Cybern Part C (Applications and Reviews)"},{"key":"9232_CR3","doi-asserted-by":"publisher","unstructured":"Batista GEAPA, Prati RC, Monard MC (2004) A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explor Newsl 6(1):20\u201329. https:\/\/doi.org\/10.1145\/1007730.1007735 (ISSN 1931-0145)","DOI":"10.1145\/1007730.1007735"},{"key":"9232_CR4","doi-asserted-by":"crossref","unstructured":"Bensalem I, Rosso P, Chikhi S (2014) Intrinsic plagiarism detection using n-gram classes. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, October 25\u201329, 2014, Doha, Qatar, A meeting of SIGDAT, a Special Interest Group of the ACL, pp 1459\u20131464. https:\/\/aclweb.org\/anthology\/D\/D14\/D14-1153.pdf","DOI":"10.3115\/v1\/D14-1153"},{"key":"9232_CR5","unstructured":"Bowyer KW, Chawla NV, Hall LO, Kegelmeyer WP (2011) SMOTE: synthetic minority over-sampling technique. CoRR, abs\/1106.1813. https:\/\/arxiv.org\/abs\/1106.1813"},{"key":"9232_CR6","doi-asserted-by":"publisher","unstructured":"Cheng N, Chandramouli R, Subbalakshmi KP (2011) Author gender identification from text. Digit Investig 8(1): 78\u201388. https:\/\/doi.org\/10.1016\/j.diin.2011.04.002 (ISSN 1742-2876)","DOI":"10.1016\/j.diin.2011.04.002"},{"key":"9232_CR7","unstructured":"Curran D (2010) An evolutionary neural network approach to intrinsic plagiarism detection. In: Proceedings of the 20th Irish Conference on Artificial Intelligence and Cognitive Science, AICS\u201909, Springer-Verlag, Berlin, Heidelberg, pp 33\u201340. https:\/\/dl.acm.org\/citation.cfm?id=1939047.1939055 (ISBN 3-642-17079-X, 978-3-642-17079-9)"},{"key":"9232_CR8","volume-title":"The principles of readability","author":"WH Dubay","year":"2004","unstructured":"Dubay WH (2004) The principles of readability. Impact Information, Costa Mesa"},{"key":"9232_CR9","unstructured":"zu Eissen SM, Stein B (2006) Intrinsic plagiarism detection. In: Lalmas M, MacFarlane A, R\u00fcger S, Tombros A, Tsikrika T, Yavlinsky A (eds) Advances in information retrieval. Springer, Berlin Heidelberg, pp 565\u2013569 (ISBN 978-3-540-33348-7)."},{"key":"9232_CR10","doi-asserted-by":"publisher","unstructured":"Holmes DI (1998) The evolution of stylometry in humanities scholarship. Lit Linguist Comput 13(3): 111\u2013117. https:\/\/doi.org\/10.1093\/llc\/13.3.111","DOI":"10.1093\/llc\/13.3.111"},{"key":"9232_CR11","doi-asserted-by":"crossref","unstructured":"Hua X, Li S, Li P, Zhu Q (2013) Research on intrinsic plagiarism detection resolution: a supervised learning approach. In: Ji D, Xiao G (eds) Chinese lexical semantics. Springer, Berlin, Heidelberg, pp 58\u201363 (ISBN 978-3-642-36337-5)","DOI":"10.1007\/978-3-642-36337-5_7"},{"key":"9232_CR12","unstructured":"Kestemont M, Luyckx K, Daelemans W (2011) Intrinsic plagiarism detection using character trigram distance scores\u2014notebook for PAN at CLEF 2011. In: Petras V, Forner P, Clough PD (eds) Notebook papers of CLEF 2011 labs and workshops, 19\u201322 September 2011, Amsterdam, The Netherlands (ISBN 978-88-904810-1-7, 2038-4963)"},{"key":"9232_CR13","doi-asserted-by":"publisher","unstructured":"Koppel M, Schler J (2004) Authorship verification as a one-class classification problem. In: Proceedings of the Twenty-first International Conference on Machine Learning, ICML, ACM \u201904, New York, NY, USA. https:\/\/doi.org\/10.1145\/1015330.1015448 (ISBN 1-58113-838-5)","DOI":"10.1145\/1015330.1015448"},{"key":"9232_CR14","doi-asserted-by":"crossref","unstructured":"Kuta M, Kitowski J (2014) Optimisation of character n-gram profiles method for intrinsic plagiarism detection. In: Rutkowski L, Korytkowski M, Scherer R, Tadeusiewicz R, Zadeh LA, Zurada JM (eds) Artificial intelligence and soft computing. Springer International Publishing, Cham, pp 500\u2013511 (ISBN 978-3-319-07176-3)","DOI":"10.1007\/978-3-319-07176-3_44"},{"key":"9232_CR15","unstructured":"Kuznetsov M, Motrenko A, Kuznetsova R, Strijov V (2016) Methods for intrinsic plagiarism detection and author diarization\u2014notebook for PAN at CLEF 2016. In: Balog K, Cappellato L, Ferro N, Macdonald C (eds) CLEF 2016 evaluation labs and workshop \u2014working notes papers, 5\u20138 September 2016, \u00c9vora, Portugal, CEUR-WS.org (ISSN 1613 0073)"},{"key":"9232_CR16","unstructured":"Lemaitre G, Nogueira F, Aridas CK (2016) Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning. CoRR. http:\/\/arxiv.org\/abs\/1609.06570"},{"key":"9232_CR17","doi-asserted-by":"crossref","unstructured":"Mihalcea RF, Radev DR (2011) Graph-based Natural Language Processing and Information Retrieval, 1st edn. Cambridge University Press, New York (ISBN 0521896134, 9780521896139)","DOI":"10.1017\/CBO9780511976247"},{"key":"9232_CR18","unstructured":"Oberreuter G, L\u2019Huillier G, R\u00edos SA, Vel\u00e1squez JD (2011) Approaches for intrinsic and external plagiarism detection\u2014notebook for PAN at CLEF 2011. In: Petras V, Forner P, Clough PD (eds) Notebook papers of CLEF 2011 labs and workshops, 19\u201322 September 2011, Amsterdam, The Netherlands (ISBN 978-88-904810-1-7, 2038-4963)"},{"issue":"9","key":"9232_CR19","doi-asserted-by":"publisher","first-page":"3756","DOI":"10.1016\/j.eswa.2012.12.082","volume":"40","author":"G Oberreuter","year":"2013","unstructured":"Oberreuter G, Vel\u00e1squez JD (2013) Text mining applied to plagiarism detection: the use of words for detecting deviations in the writing style. Expert Syst Appl 40(9):3756\u20133763. https:\/\/doi.org\/10.1016\/j.eswa.2012.12.082","journal-title":"Expert Syst Appl"},{"key":"9232_CR20","unstructured":"Potthast M, Eiselt A, Cedeo AB, Stein B, Rosso P (2011) Overview of the 3rd international competition on plagiarism detection. In: Working Notes Papers of the CLEF 2011 Evaluation"},{"key":"9232_CR21","unstructured":"Potthast M, Stein B, Eiselt A, Weimar BU, Cedeo AB, Rosso P (2009) Overview of the 1st international competition on plagiarism detection. In: SEPLN 2009 Workshop on Uncovering Plagiarism, Authorship, and Social Software Misuse (PAN 09), CEUR-WS.org, pp. 1\u20139"},{"key":"9232_CR22","doi-asserted-by":"crossref","unstructured":"Ranatunga R, Atukorale A, Hewagamage K (2011) Intrinsic plagiarism detection with Kohonen self organizing maps. In: 2011 International conference on advances in ICT for emerging regions (ICTer). IEEE, pp 125","DOI":"10.1109\/ICTer.2011.6075041"},{"key":"9232_CR23","unstructured":"Rosso P, Rangel F, Potthast M, Stamatatos E, Tschuggnall M, Stein B (2016) Overview of the PAN\u20192016 - new challenges for authorship analysis: cross-genre profiling, clustering, diarization, and obfuscation. In: 7th Int. Conf. of CLEF on experimental IR meets multilinguality, multimodality, and interaction, CLEF 2016, LNCS(9822), Springer, pp 332\u2013350"},{"key":"9232_CR24","unstructured":"Seaward L, Matwin S (2009) Intrinsic plagiarism detection using complexity analysis. In: Stein B et al (eds) SEPLN 2009 Workshop on uncovering plagiarism, authorship, and social software misuse (PAN 09). Universidad Polit\u00e9cnica de Valencia and CEUR-WS.org, pp 56\u201361 (ISSN 1613-0073)"},{"key":"9232_CR25","unstructured":"Sittar A, Iqbal HR, Nawab RMA (2016) Author diarization using cluster-distance approach\u2014notebook for PAN at CLEF 2016. In: Balog K, Cappellato L, Ferro N, Macdonald C (eds) CLEF 2016 evaluation labs and workshop\u2014working notes papers, 5\u20138 September 2016, \u00c9vora, Portugal. CEUR-WS.org (ISSN 1613-0073)"},{"key":"9232_CR26","unstructured":"Stamatatos E (2009a) Intrinsic plagiarism detection using character n-gram profiles. In: Stein B, Rosso P, Stamatatos E, Koppel M, Agirre E (eds) SEPLN 2009 workshop on uncovering plagiarism, authorship, and social software misuse (PAN 09), pp 38\u201346"},{"key":"9232_CR27","doi-asserted-by":"publisher","unstructured":"Stamatatos E (2009b) A survey of modern authorship attribution methods. J Am Soc Inf Sci Technol 60(3):538\u2013556. https:\/\/doi.org\/10.1002\/asi.v60:3 (ISSN 1532-2882)","DOI":"10.1002\/asi.v60:3"},{"key":"9232_CR28","doi-asserted-by":"crossref","unstructured":"Stamatatos E, Daelemans W, Verhoeven B, Juola P, L\u00f3pez-L\u00f3pez A, Potthast M, Stein B (2015) Overview of the author identification task at pan. In: CLEF 2015 Evaluation Labs and Workshop\u2014Working Notes Papers. CEUR, Toulouse (2015\/09\/10 2015)","DOI":"10.1007\/978-3-319-24027-5_49"},{"key":"9232_CR29","doi-asserted-by":"publisher","unstructured":"Stein B, Lipka N, Prettenhofer P (2011) Intrinsic plagiarism analysis. Lang Resour Eval 45(1):63\u201382. https:\/\/doi.org\/10.1007\/s10579-010-9115-y (ISSN 1574-020X)","DOI":"10.1007\/s10579-010-9115-y"},{"key":"9232_CR30","doi-asserted-by":"crossref","unstructured":"Tang Y, Zhang Y, Chawla NV, Krasser S (2009) Svms modeling for highly imbalanced classification. IEEE Trans Syst Man Cybern Part B (Cybern) 39:281\u2013288","DOI":"10.1109\/TSMCB.2008.2002909"},{"key":"9232_CR31","doi-asserted-by":"crossref","unstructured":"Tschuggnall M, Specht G (2012) Plag-inn: Intrinsic plagiarism detection using grammar trees. In: Bouma G, Ittoo A, M\u00e9tais E, Wortmann H (eds) Natural Language Processing and Information Systems. Springer, Berlin, Heidelberg, pp 284\u2013289 (ISBN 978-3-642-31178-9)","DOI":"10.1007\/978-3-642-31178-9_35"},{"key":"9232_CR32","doi-asserted-by":"crossref","unstructured":"Tschuggnall M, Specht G (2013) Using grammar-profiles to intrinsically expose plagiarism in text documents. In: M\u00e9tais E, Meziane F, Saraee M, Sugumaran V, Vadera S (eds) Natural Language Processing and Information Systems. Springer, Berlin, Heidelberg, pp 297\u2013302 (ISBN 978-3-642-38824-8)","DOI":"10.1007\/978-3-642-38824-8_28"},{"key":"9232_CR33","doi-asserted-by":"crossref","unstructured":"Wilson DL (1972) Asymptotic properties of nearest neighbor rules using edited data. IEEE Trans Syst Man Cybern 2(3):408\u2013421 (ISSN 0018-9472)","DOI":"10.1109\/TSMC.1972.4309137"}],"container-title":["Evolving Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12530-018-9232-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s12530-018-9232-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s12530-018-9232-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T19:52:04Z","timestamp":1751745124000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s12530-018-9232-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7,13]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,9]]}},"alternative-id":["9232"],"URL":"https:\/\/doi.org\/10.1007\/s12530-018-9232-1","relation":{},"ISSN":["1868-6478","1868-6486"],"issn-type":[{"value":"1868-6478","type":"print"},{"value":"1868-6486","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7,13]]},"assertion":[{"value":"5 January 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}