{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T06:22:34Z","timestamp":1761805354074,"version":"3.41.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T00:00:00Z","timestamp":1516838400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2018,7]]},"DOI":"10.1007\/s00607-018-0587-8","type":"journal-article","created":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T14:36:34Z","timestamp":1516890994000},"page":"741-756","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Document embeddings learned on various types of n-grams for cross-topic authorship attribution"],"prefix":"10.1007","volume":"100","author":[{"given":"Helena","family":"G\u00f3mez-Adorno","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan-Pablo","family":"Posadas-Dur\u00e1n","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grigori","family":"Sidorov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Pinto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,1,25]]},"reference":[{"issue":"5","key":"587_CR1","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/MIS.2005.81","volume":"20","author":"A Abbasi","year":"2005","unstructured":"Abbasi A, Chen H (2005) Applying authorship analysis to extremist-group web forum messages. IEEE Intell Syst 20(5):67\u201375","journal-title":"IEEE Intell Syst"},{"key":"587_CR2","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio Y, Ducharme R, Vincent P, Jauvin C (2003) A neural probabilistic language model. J Mach Learn Res 3:1137\u20131155","journal-title":"J Mach Learn Res"},{"key":"587_CR3","unstructured":"Black PE (2015) Fisher-yates shuffle. In: Pieterse V, Black PE (eds) Dictionary of algorithms and data structures [online]. Available from https:\/\/www.nist.gov\/dads\/HTML\/fisherYatesShuffle.html"},{"key":"587_CR4","first-page":"441","volume":"21","author":"M Coulthard","year":"2012","unstructured":"Coulthard M (2012) On admissible linguistic evidence. J Law Policy 21:441","journal-title":"J Law Policy"},{"key":"587_CR5","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, ACL \u201911, pp 288\u2013298"},{"key":"587_CR6","unstructured":"G\u00f3mez-Adorno H, Sidorov G, Pinto D, Markov I (2015) A graph based authorship identification approach. In: Working notes papers of the CLEF 2015 evaluation labs, CLEF \u201915, vol 1391"},{"issue":"9","key":"587_CR7","doi-asserted-by":"publisher","first-page":"1374","DOI":"10.3390\/s16091374","volume":"16","author":"H G\u00f3mez-Adorno","year":"2016","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","journal-title":"Sensors"},{"key":"587_CR8","doi-asserted-by":"crossref","unstructured":"Iyyer M, Manjunatha V, Boyd-Graber JL, Daum\u00e9\u00a0III H (2015) Deep unordered composition rivals syntactic methods for text classification. In: Association for computational linguistics, ACl \u201915, pp 1681\u20131691","DOI":"10.3115\/v1\/P15-1162"},{"key":"587_CR9","doi-asserted-by":"crossref","unstructured":"Kalchbrenner N, Grefenstette E, Blunsom P (2014) A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188","DOI":"10.3115\/v1\/P14-1062"},{"issue":"3","key":"587_CR10","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1080\/0013838X.2012.668793","volume":"93","author":"M Kestemont","year":"2012","unstructured":"Kestemont M, Luyckx K, Daelemans W, Crombez T (2012) Cross-genre authorship verification using unmasking. English Stud 93(3):340\u2013356","journal-title":"English Stud"},{"key":"587_CR11","unstructured":"Kiros R, Zhu Y, Salakhutdinov RR, Zemel R, Urtasun R, Torralba A, Fidler S (2015) Skip-thought vectors. In: Advances in neural information processing systems, NIPS \u201915, pp 3294\u20133302"},{"key":"587_CR12","first-page":"1261","volume":"8","author":"M Koppel","year":"2007","unstructured":"Koppel M, Schler J, Bonchek-Dokow E (2007) Measuring differentiability: unmasking pseudonymous authors. J Mach Learn Res 8:1261\u20131276","journal-title":"J Mach Learn Res"},{"key":"587_CR13","doi-asserted-by":"crossref","unstructured":"Koppel M, Seidman S (2013) Automatically identifying pseudepigraphic texts. In: Proceedings of the 2013 conference on empirical methods in natural language processing, EMNLP \u201913, pp 1449\u20131454","DOI":"10.18653\/v1\/D13-1151"},{"key":"587_CR14","unstructured":"Le QV, Mikolov T (2014) Distributed representations of sentences and documents. In: Proceedings of the 31th international conference on machine learning, ICML \u201914, pp 1188\u20131196"},{"key":"587_CR15","unstructured":"Li B, Liu T, Du X, Zhang D, Zhao Z (2015) Learning document embeddings by predicting n-grams for sentiment classification of long movie reviews. arXiv preprint arXiv:1512.08183"},{"key":"587_CR16","unstructured":"Maas AL, Daly RE, Pham PT, Huang D, Ng AY, Potts C (2011) Learning word vectors for sentiment analysis. In: Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies-vol 1, ACl \u201911, pp 142\u2013150"},{"key":"587_CR17","doi-asserted-by":"crossref","unstructured":"Madigan D, Genkin A, Lewis DD, Fradkin D (2005) Bayesian multinomial logistic regression for author identification. In: AIP conference proceedings, vol 803, pp 509\u2013516. AIP","DOI":"10.1063\/1.2149832"},{"key":"587_CR18","unstructured":"Markov I, Stamatatos E, Sidorov G (2017) Improving cross-topic authorship attribution: the role of pre-processing. In: 18th International conference on computational linguistics and intelligent text processing, CICLING \u201917"},{"key":"587_CR19","unstructured":"Mikolov T, Yih WT, Zweig G (2013) Linguistic regularities in continuous space word representations. In: Conference of the North American chapter of the association for computational linguistics: human language technologies, NAACL \u201913, pp 746\u2013751"},{"key":"587_CR20","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"issue":"3","key":"587_CR21","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/s00500-016-2446-x","volume":"21","author":"Juan-Pablo Posadas-Dur\u00e1n","year":"2016","unstructured":"Posadas-Dur\u00e1n JP, G\u00f3mez-Adorno H, Sidorov G, Batyrshin I, Pinto D, Chanona-Hern\u00e1ndez L Application of the distributed document representation in the authorship attribution task for small corpora. Soft Comput 21(3):1\u201313","journal-title":"Soft Computing"},{"key":"587_CR22","first-page":"9","volume-title":"Lecture Notes in Computer Science","author":"Juan-Pablo Posadas-Duran","year":"2014","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, MICAI \u201914, pp 9\u201317"},{"key":"587_CR23","unstructured":"Posadas-Dur\u00e1n JP, Sidorov G, Batyrshin I, Mirasol-Mel\u00e9ndez E (2015) Author verification using syntactic n-grams. In: Working notes papers of the CLEF 2015 evaluation labs, CLEF \u201915, vol 1391"},{"key":"587_CR24","first-page":"393","volume-title":"Lecture Notes in Computer Science","author":"Martin Potthast","year":"2016","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: Advances in information retrieval\u201438th European conference on IR research, ECIR \u201916, pp 393\u2013407"},{"key":"587_CR25","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: Conference of the North American chapter of the association for computational linguistics: human language technologies, NAACL \u20192015, pp 93\u2013102","DOI":"10.3115\/v1\/N15-1010"},{"key":"587_CR26","unstructured":"Sapkota U, Solorio T, Montes-y G\u00f3mez M, Bethard S, Rosso P (2014) Cross-topic authorship attribution: will out-of-topic data help? In: The 25th international conference on computational linguistics: technical papers, COLING \u201914, pp 1228\u20131237"},{"key":"587_CR27","unstructured":"Schwartz MB (2016) An examination of cross-domain authorship attribution techniques. CUNY Academic Works. https:\/\/academicworks.cuny.edu\/gc_etds\/1573 . Accessed 16 Jan 2018"},{"issue":"3","key":"587_CR28","doi-asserted-by":"publisher","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":"587_CR29","doi-asserted-by":"crossref","unstructured":"Socher R, Perelygin A, Wu JY, Chuang J, Manning CD, Ng AY, Potts C (2013) Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 conference on empirical methods in natural language processing, EMNLP \u201913, pp 1631\u20131642","DOI":"10.18653\/v1\/D13-1170"},{"issue":"3","key":"587_CR30","doi-asserted-by":"publisher","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":"2","key":"587_CR31","first-page":"421","volume":"21","author":"E Stamatatos","year":"2013","unstructured":"Stamatatos E (2013) On the robustness of authorship attribution based on character n-gram features. J Law Policy 21(2):421\u2013439","journal-title":"J Law Policy"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00607-018-0587-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-018-0587-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-018-0587-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:42:12Z","timestamp":1751244132000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00607-018-0587-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1,25]]},"references-count":31,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2018,7]]}},"alternative-id":["587"],"URL":"https:\/\/doi.org\/10.1007\/s00607-018-0587-8","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"type":"print","value":"0010-485X"},{"type":"electronic","value":"1436-5057"}],"subject":[],"published":{"date-parts":[[2018,1,25]]},"assertion":[{"value":"19 June 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 January 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}