{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:53:35Z","timestamp":1777708415904,"version":"3.51.4"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2016,11,28]],"date-time":"2016-11-28T00:00:00Z","timestamp":1480291200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2017,2]]},"DOI":"10.1007\/s00500-016-2446-x","type":"journal-article","created":{"date-parts":[[2016,11,28]],"date-time":"2016-11-28T08:42:30Z","timestamp":1480322550000},"page":"627-639","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Application of the distributed document representation in the authorship attribution task for small corpora"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9496-1328","authenticated-orcid":false,"given":"Juan-Pablo","family":"Posadas-Dur\u00e1n","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helena","family":"G\u00f3mez-Adorno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grigori","family":"Sidorov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ildar","family":"Batyrshin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Pinto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liliana","family":"Chanona-Hern\u00e1ndez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,28]]},"reference":[{"issue":"2","key":"2446_CR1","doi-asserted-by":"crossref","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: Appl Rev 42(2):133\u2013149","journal-title":"IEEE Trans Syst Man Cybern Part C: Appl Rev"},{"key":"2446_CR2","unstructured":"Argamon S, Juola P (2011) Overview of the international authorship identification competition at pan-2011. In: CLEF (Notebook Papers\/Labs\/Workshop)"},{"issue":"2","key":"2446_CR3","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1145\/1461928.1461959","volume":"52","author":"S Argamon","year":"2009","unstructured":"Argamon S, Koppel M, Pennebaker JW, Schler J (2009) Automatically profiling the author of an anonymous text. Commun ACM 52(2):119\u2013123","journal-title":"Commun ACM"},{"key":"2446_CR4","volume-title":"Introduction to functional programming","author":"R Bird","year":"1988","unstructured":"Bird R, Wadler P (1988) Introduction to functional programming, vol 1. Prentice Hall, New York"},{"key":"2446_CR5","doi-asserted-by":"crossref","unstructured":"Brocardo ML, Traore I, Saad S, Woungang I (2013) Authorship verification for short messages using stylometry. In: IEEE international conference on computer, information and telecommunication systems (CITS), 2013, pp 1\u20136","DOI":"10.1109\/CITS.2013.6705711"},{"issue":"1","key":"2446_CR6","first-page":"1","volume":"4","author":"CE Chaski","year":"2005","unstructured":"Chaski CE (2005) Who\u2019s at the keyboard? Authorship attribution in digital evidence investigations. Int J Digit Evid 4(1):1\u201313","journal-title":"Int J Digit Evid"},{"key":"2446_CR7","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1016\/j.eswa.2015.10.001","volume":"54","author":"L Cleofas-S\u00e1nchez","year":"2016","unstructured":"Cleofas-S\u00e1nchez L, S\u00e1nchez J, Garc\u00eda V, Valdovinos R (2016) Associative learning on imbalanced environments: an empirical study. Expert Syst Appl 54:387\u2013397","journal-title":"Expert Syst Appl"},{"key":"2446_CR8","unstructured":"Escalante HJ, Solorio T, Montes-y G\u00f3mez M (2011) Local histograms of character n-grams for authorship attribution. In: Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies , vol 1. Association for Computational Linguistics, Stroudsburg, HLT \u201911, pp 288\u2013298"},{"key":"2446_CR9","unstructured":"Franco-Salvador M, Rosso P, Rangel F (2015) Distributed representations of words and documents for discriminating similar languages. In: Proceeding of the RANLP Joint Workshop on language technology for closely related languages, varieties and dialects (LT4VarDial)"},{"key":"2446_CR10","doi-asserted-by":"crossref","unstructured":"G\u00f3mez-Adorno H, Sidorov G, Pinto D, Vilari\u00f1o D, Gelbukh A (2016) Automatic authorship detection using textual patterns extracted from integrated syntactic graphs.Sensors 16(9):1374","DOI":"10.3390\/s16091374"},{"issue":"3","key":"2446_CR11","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1093\/llc\/13.3.111","volume":"13","author":"DI Holmes","year":"1998","unstructured":"Holmes DI (1998) The evolution of stylometry in humanities scholarship. Lit Linguist Comput 13(3):111\u2013117","journal-title":"Lit Linguist Comput"},{"key":"2446_CR12","unstructured":"Houvardas J, Stamatatos E (2006) Stamatatos e.: N-gram feature selection for authorship identification. In: 12th international conference on artificial intelligence: methodology, systems, applications. Springer, pp 77\u201386"},{"key":"2446_CR13","unstructured":"Juola P (2004) Ad-hoc authorship attribution competition. In: Proceedings of the joint conference of the association for computers and the humanities and the association for literary and linguistic computing, pp 175\u2013176"},{"key":"2446_CR14","unstructured":"Juola P (2012) An overview of the traditional authorship attribution subtask. In: CLEF (Online Working Notes\/Labs\/Workshop)"},{"key":"2446_CR15","first-page":"255","volume":"3","author":"V Ke\u0161elj","year":"2003","unstructured":"Ke\u0161elj V, Peng F, Cercone N, Thomas C (2003) N-gram-based author profiles for authorship attribution. Proceedings of the conference pacific association for computational linguistics, PACLING 3:255\u2013264","journal-title":"Proceedings of the conference pacific association for computational linguistics, PACLING"},{"key":"2446_CR16","unstructured":"Kiros R, Zemel RS, Salakhutdinov RR, (2014) A multiplicative model for learning distributed text-based attribute representations. In: Advances in neural information processing systems 27: annual conference on neural information processing systems 2014. Montreal, pp. 8\u201313"},{"key":"2446_CR17","unstructured":"Le QV, Mikolov T (2014) Distributed representations of sentences and documents. In: Proceedings of the 31th international conference on machine learning, ICML 2014, Beijing, pp 1188\u20131196"},{"key":"2446_CR18","first-page":"361","volume":"5","author":"DD Lewis","year":"2004","unstructured":"Lewis DD, Yang Y, Rose TG, Li F (2004) Rcv1: a new benchmark collection for text categorization research. J Mach Learn Res 5:361\u2013397","journal-title":"J Mach Learn Res"},{"key":"2446_CR19","doi-asserted-by":"crossref","unstructured":"Li R, Shindo H (2015) Distributed document representation for document classification. In: Cao T, Lim EP, Zhou ZH, Ho TB, Cheung D, Motoda H (eds) Advances in knowledge discovery and data mining, Lecture Notes in Computer Science, vol 9077, Springer International Publishing, pp 212\u2013225","DOI":"10.1007\/978-3-319-18038-0_17"},{"issue":"4","key":"2446_CR20","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1093\/llc\/8.4.203","volume":"8","author":"R Matthews","year":"1993","unstructured":"Matthews R, Merriam T (1993) Neural computation in stylometry i: an application to the works of shakespeare and fletcher. Lit Linguist Comput 8(4):203\u2013209","journal-title":"Lit Linguist Comput"},{"key":"2446_CR21","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013a) Efficient estimation of word representations in vector space. CoRR abs\/1301.3781, http:\/\/arxiv.org\/abs\/1301.3781"},{"key":"2446_CR22","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013b) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems 26: 27th annual conference on neural information processing systems 2013. Proceedings of a meeting held December 5\u20138, 2013, Lake Tahoe, pp 3111\u20133119"},{"key":"2446_CR23","unstructured":"Mikolov T, Yih WT, Zweig G (2013c) Linguistic regularities in continuous space word representations. In: NAACL HLT, Atlanta, June 9, 14, pp 746\u2013751"},{"issue":"86","key":"2446_CR24","doi-asserted-by":"crossref","first-page":"463","DOI":"10.4067\/S0718-09342014000300006","volume":"47","author":"S Miranda","year":"2014","unstructured":"Miranda S, Gelbukh A, Sidorov G (2014) Generating summaries by means of synthesis of conceptual graphs. Rev Signos 47(86):463","journal-title":"Rev Signos"},{"key":"2446_CR25","unstructured":"Mnih A, Hinton GE (2009) A scalable hierarchical distributed language model. In: Koller D, Schuurmans D, Bengio Y, Bottou L (eds) Advances in neural information processing systems 21. Curran Associates Inc., pp 1081\u20131088"},{"issue":"302","key":"2446_CR26","first-page":"275","volume":"58","author":"F Mosteller","year":"1963","unstructured":"Mosteller F, Wallace DL (1963) Inference in an authorship problem: a comparative study of discrimination methods applied to the authorship of the disputed federalist papers. J Am Stat Assoc 58(302):275\u2013309","journal-title":"J Am Stat Assoc"},{"key":"2446_CR27","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP 2014), pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"2446_CR28","doi-asserted-by":"crossref","unstructured":"Plakias S, Stamatatos E (2008) Tensor space models for authorship identification. In: Darzentas J, Vouros G, Vosinakis S, Arnellos A (eds) Artificial intelligence: theories, models and applications, Springer, Lecture Notes in Computer Science, vol 5138, pp 239\u2013249","DOI":"10.1007\/978-3-540-87881-0_22"},{"key":"2446_CR29","unstructured":"Posadas-Dur\u00e1n J, G\u00f3mez-Adorno H, Markov I, Sidorov G, Batyrshin I, Gelbukh A , Pichardo- Lagunas O (2015) Syntactic N-grams as Features for the Author Profiling Task. In: Proceedings conference and labs of the evaluation forum"},{"key":"2446_CR30","doi-asserted-by":"crossref","unstructured":"Posadas-Duran JP, Sidorov G, Batyrshin I (2014) Complete syntactic N-grams as style markers for authorship attribution. In: Mexican international conference on artificial intelligence, Springer, pp 9\u201317","DOI":"10.1007\/978-3-319-13647-9_2"},{"key":"2446_CR31","doi-asserted-by":"crossref","unstructured":"Potthast M, Braun S, Buz T, Duffhauss F, Friedrich F, G\u00fclzow JM, K\u00f6hler J, L\u00f6tzsch W, M\u00fcller F, M\u00fcller ME, Pa\u00dfmann R, Reinke B, Rettenmeier L, Rometsch T, Sommer T, Tr\u00e4ger M, Wilhelm S, Stein B, Stamatatos E, Hagen M (2016) Who wrote the web? Revisiting influential author identification research applicable to information retrieval. In: Proceedings on advances in information retrieval - 38th European conference on IR research, ECIR 2016, Padua, March 20\u201323, 2016 , pp 393\u2013407","DOI":"10.1007\/978-3-319-30671-1_29"},{"key":"2446_CR32","unstructured":"Rhodes D (2015) Author attribution with cnns. Tech. rep., CS224, Stanford University"},{"key":"2446_CR33","doi-asserted-by":"crossref","unstructured":"Sanchez-Perez MA, Gelbukh A, Sidorov G (2015) Adaptive algorithm for plagiarism detection: the best performing approach at pan 2014 text alignment competition. In: International conference of the cross language evaluation forum for european languages, Springer, pp 402\u2013413","DOI":"10.1007\/978-3-319-24027-5_42"},{"key":"2446_CR34","doi-asserted-by":"crossref","unstructured":"Sapkota U, Bethard S, Montes-y G\u00f3mez M, Solorio T (2015) Not all character n-grams are created equal: a study in authorship attribution. In: Human language technologies: The 2015 annual conference of the North American chapter of the ACL, pp 93\u2013102","DOI":"10.3115\/v1\/N15-1010"},{"key":"2446_CR35","doi-asserted-by":"crossref","unstructured":"Segarra S, Eisen M, Ribeiro A (2013) Authorship attribution using function words adjacency networks. In: IEEE international conference on acoustics, speech and signal processing, ICASSP 2013, Vancouver, May 26-31, 2013, pp 5563\u20135567","DOI":"10.1109\/ICASSP.2013.6638728"},{"issue":"3","key":"2446_CR36","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1016\/j.eswa.2013.08.015","volume":"41","author":"G Sidorov","year":"2014","unstructured":"Sidorov G, Velasquez F, Stamatatos E, Gelbukh A, Chanona-Hern\u00e1ndez L (2014) Syntactic n-grams as machine learning features for natural language processing. Expert Syst Appl 41(3):853\u2013860","journal-title":"Expert Syst Appl"},{"key":"2446_CR37","unstructured":"Socher R, Bauer J, Manning CD, Ng AY (2013a) Parsing with compositional vector grammars. In: Proceedings of the ACL conference"},{"key":"2446_CR38","doi-asserted-by":"crossref","unstructured":"Socher R, Perelygin A, Wu JY, Chuang J, Manning CD, Ng AY, Potts C (2013b) Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the conference on empirical methods in natural language processing (EMNLP), vol 1631, p 1642","DOI":"10.18653\/v1\/D13-1170"},{"issue":"2","key":"2446_CR39","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1016\/j.ipm.2007.05.012","volume":"44","author":"E Stamatatos","year":"2008","unstructured":"Stamatatos E (2008) Author identification: using text sampling to handle the class imbalance problem. Inf Process Manag 44(2):790\u2013799","journal-title":"Inf Process Manag"},{"issue":"3","key":"2446_CR40","doi-asserted-by":"crossref","first-page":"538","DOI":"10.1002\/asi.21001","volume":"60","author":"E Stamatatos","year":"2009","unstructured":"Stamatatos E (2009) A survey of modern authorship attribution methods. J Am Soc Inf Sci Technol 60(3):538\u2013556","journal-title":"J Am Soc Inf Sci Technol"},{"issue":"12","key":"2446_CR41","doi-asserted-by":"crossref","first-page":"2512","DOI":"10.1002\/asi.21630","volume":"62","author":"E Stamatatos","year":"2011","unstructured":"Stamatatos E (2011) Plagiarism detection using stopword n-grams. J Am Soc Inf Sci Technol 62(12):2512\u20132527","journal-title":"J Am Soc Inf Sci Technol"},{"key":"2446_CR42","unstructured":"Stamatatos E (2013) On the robustness of authorship attribution based on character n-gram features. J Law Policy 21(2):421\u2013439"},{"key":"2446_CR43","doi-asserted-by":"crossref","unstructured":"Stamatatos E, Fakotakis N, Kokkinakis G (2001) Computer-based authorship attribution without lexical measures. Comput Humanit 35(2):193\u2013214","DOI":"10.1023\/A:1002681919510"},{"issue":"1","key":"2446_CR44","first-page":"7","volume":"6","author":"JVC Trejo","year":"2015","unstructured":"Trejo JVC, Sidorov G, Miranda-Jim\u00e9nez S, Ibarra MAM, Mart\u00ednez RC (2015) Latent dirichlet allocation complement in the vector space model for multi-label text classification. IJCOPI 6(1):7\u201319","journal-title":"IJCOPI"},{"key":"2446_CR45","unstructured":"Turian J, Ratinov L, Bengio Y (2010) Word representations: A simple and general method for semisupervised learning. In: Proceedings of the 48th annual meeting of the association for computational linguistics, pp 384\u2013394"},{"key":"2446_CR46","unstructured":"Wiemer-Hastings P, Wiemer-Hastings K, Graesser A (2004) Latent semantic analysis. In: Proceedings of the 16th international joint conference on artificial intelligence, pp 1\u201314"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-016-2446-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00500-016-2446-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-016-2446-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T22:10:17Z","timestamp":1749766217000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00500-016-2446-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11,28]]},"references-count":46,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,2]]}},"alternative-id":["2446"],"URL":"https:\/\/doi.org\/10.1007\/s00500-016-2446-x","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"value":"1432-7643","type":"print"},{"value":"1433-7479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,11,28]]}}}