{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:57:04Z","timestamp":1775246224368,"version":"3.50.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319771151","type":"print"},{"value":"9783319771168","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-77116-8_21","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T23:56:00Z","timestamp":1539042960000},"page":"289-302","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Improving Cross-Topic Authorship Attribution: The Role of Pre-Processing"],"prefix":"10.1007","author":[{"given":"Ilia","family":"Markov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Efstathios","family":"Stamatatos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grigori","family":"Sidorov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,10]]},"reference":[{"key":"21_CR1","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1002\/asi.21001","volume":"60","author":"E Stamatatos","year":"2009","unstructured":"Stamatatos, E.: A survey of modern authorship attribution methods. J. Am. Soc. Inf. Sci. Technol. 60, 538\u2013556 (2009)","journal-title":"J. Am. Soc. Inf. Sci. Technol."},{"key":"21_CR2","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.: Applying authorship analysis to extremist-group Web forum messages. IEEE Intell. Syst. 20, 67\u201375 (2005)","journal-title":"IEEE Intell. Syst."},{"key":"21_CR3","first-page":"1","volume":"4","author":"CE Chaski","year":"2005","unstructured":"Chaski, C.E.: Who\u2019s at the keyboard? Authorship attribution in digital evidence investigations. Int. J. Digit. Evid. 4, 1\u201313 (2005)","journal-title":"Int. J. Digit. Evid."},{"key":"21_CR4","first-page":"441","volume":"21","author":"M Coulthard","year":"2013","unstructured":"Coulthard, M.: On admissible linguistic evidence. J. Law Policy 21, 441\u2013466 (2013)","journal-title":"J. Law Policy"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Koppel, M., Seidman, S.: Automatically identifying pseudepigraphic texts. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, (EMNLP\u201913), pp. 1449\u20131454 (2013)","DOI":"10.18653\/v1\/D13-1151"},{"key":"21_CR6","first-page":"427","volume":"21","author":"E Stamatatos","year":"2013","unstructured":"Stamatatos, E.: On the robustness of authorship attribution based on character n-gram features. J. Law Policy 21, 427\u2013439 (2013)","journal-title":"J. Law Policy"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Luyckx, K., Daelemans, W.: Authorship attribution and verification with many authors and limited data. In: Proceedings of the 22nd International Conference on Computational Linguistics (COLING\u201908), pp. 513\u2013520 (2008)","DOI":"10.3115\/1599081.1599146"},{"key":"21_CR8","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/11861461_10","volume-title":"Artificial Intelligence: Methodology, Systems, and Applications","author":"John Houvardas","year":"2006","unstructured":"Houvardas, J., Stamatatos, E.: N-gram feature selection for authorship identification. In: Proceedings of Artificial Intelligence: Methodologies, Systems, and Applications (AIMSA\u201906), pp. 77\u201386 (2006)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Kestemont, M.: Function words in authorship attribution. From black magic to theory? In: Proceedings of the 3rd Workshop on Computational Linguistics for Literature (EACL\u201914), pp. 59\u201366 (2014)","DOI":"10.3115\/v1\/W14-0908"},{"key":"21_CR10","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/978-3-642-37256-8_37","volume-title":"Computational Linguistics and Intelligent Text Processing","author":"Walter Daelemans","year":"2013","unstructured":"Daelemans, W.: Explanation in computational stylometry. In: Proceedings of the 14th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing\u201913), pp. 451\u2013462 (2013)"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Sapkota, U., Bethard, S., Montes-y-G\u00f3mez, M., Solorio, T.: Not all character n-grams are created equal: a study in authorship attribution. In: Proceedings of the 2015 Annual Conference of the North American Chapter of the ACL: Human Language Technologies (NAACL-HLT\u201915), pp. 93\u2013102 (2015)","DOI":"10.3115\/v1\/N15-1010"},{"key":"21_CR12","unstructured":"Hedegaard, S., Simonsen, J.G.: Lost in translation: authorship attribution using frame semantics. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (HLT\u201911), pp. 65\u201370 (2011)"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Schwartz, R., Tsur, O., Rappoport, A., Koppel, M.: Authorship attribution of micro-messages. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing (EMNLP\u201913), pp. 1880\u20131891 (2013)","DOI":"10.18653\/v1\/D13-1193"},{"key":"21_CR14","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.: Syntactic n-grams as machine learning features for natural language processing. Expert Syst. Appl. 41, 853\u2013860 (2014)","journal-title":"Expert Syst. Appl."},{"key":"21_CR15","unstructured":"G\u00f3mez-Adorno, H., Sidorov, G., Pinto, D., Markov, I.: A graph based authorship identification approach. In: Working Notes Papers of the CLEF 2015 Evaluation Labs (CLEF\u201915), vol. 1391. CEUR (2015)"},{"key":"21_CR16","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1093\/llc\/fqm020","volume":"22","author":"J Grieve","year":"2007","unstructured":"Grieve, J.: Quantitative authorship attribution: an evaluation of techniques. Lit. Linguist. Comput. 22, 251\u2013270 (2007)","journal-title":"Lit. Linguist. Comput."},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Stamatatos, E.: Author identification using imbalanced and limited training texts. In: Proceedings of the 18th International Conference on Database and Expert Systems Applications (DEXA\u201907), pp. 237\u2013241 (2007)","DOI":"10.1109\/DEXA.2007.4312893"},{"key":"21_CR18","unstructured":"Escalante, H.J., Solorio, T., Montes-y-G\u00f3mez, M.: 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 (HLT\u201911), pp. 288\u2013298 (2011)"},{"key":"21_CR19","unstructured":"Sapkota, U., Solorio, T., Montes-y-G\u00f3mez, M., Bethard, S., Rosso, P.: Cross-topic authorship attribution: will out-of-topic data help? In: Proceedings of the 25th International Conference on Computational Linguistics (COLING\u201914), pp. 1228\u20131237 (2014)"},{"key":"21_CR20","doi-asserted-by":"crossref","unstructured":"Khmelev, D.V., Teahan, W.J.: A repetition based measure for verification of text collections and for text categorization. In: Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR\u201903), pp. 104\u2013110 (2003)","DOI":"10.1145\/860454.860456"},{"key":"21_CR21","first-page":"300","volume-title":"Lecture Notes in Computer Science","author":"Yuval Marton","year":"2005","unstructured":"Marton, Y., Wu, N., Hellerstein, L.: On compression-based text classification. In: Proceedings of the 27th European conference on Advances in Information Retrieval Research (ECIR\u201905), pp. 300\u2013314 (2005)"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Peng, F., Schuurmans, D., Keselj, V., Wang, S.: Language independent authorship attribution with character level n-grams. In: Proceedings of the 10th Conference of the European Chapter of the Association for Computational Linguistics (EACL\u201903), pp. 267\u2013274 (2003)","DOI":"10.3115\/1067807.1067843"},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Qian, T., Liu, B., Chen, L., Peng, Z.: Tri-training for authorship attribution with limited training data. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (ACL\u201914), pp. 345\u2013351 (2014)","DOI":"10.3115\/v1\/P14-2057"},{"key":"21_CR24","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1162\/089120100750105920","volume":"26","author":"E Stamatatos","year":"2000","unstructured":"Stamatatos, E., Fakotakis, N., Kokkinakis, G.: Automatic text categorization in terms of genre and author. Comput. Linguist. 26, 471\u2013495 (2000)","journal-title":"Comput. Linguist."},{"key":"21_CR25","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1145\/604264.604272","volume":"30","author":"OY Vel de","year":"2001","unstructured":"de Vel, O.Y., Anderson, A., Corney, M., Mohay, G.M.: Mining email content for author identification forensics. SIGMOD Rec. 30, 55\u201364 (2001)","journal-title":"SIGMOD Rec."},{"key":"21_CR26","first-page":"1261","volume":"8","author":"M Koppel","year":"2007","unstructured":"Koppel, M., Schler, J., Bonchek-Dokow, E.: Measuring differentiability: unmasking pseudonymous authors. J. Mach. Learn. Res. 8, 1261\u20131276 (2007)","journal-title":"J. Mach. Learn. Res."},{"key":"21_CR27","unstructured":"Stamatatos, E., Daelemans, W., Verhoeven, B., Juola, P., L\u00f3pez-L\u00f3pez, A., Potthast, M., Stein, B.: Overview of the author identification task at PAN 2015. In: Working Notes of CLEF 2015-Conference and Labs of the Evaluation Forum (2015)"},{"key":"21_CR28","first-page":"361","volume":"5","author":"DD Lewis","year":"2004","unstructured":"Lewis, D.D., Yang, Y., Rose, T.G., Li, F.: RCV1: a new benchmark collection for text categorization research. J. Mach. Learn. Res. 5, 361\u2013397 (2004)","journal-title":"J. Mach. Learn. Res."},{"key":"21_CR29","doi-asserted-by":"crossref","unstructured":"Finkel, J.R., Grenager, T., Manning, C.: Incorporating non-local information into information extraction systems by Gibbs sampling. In: Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL\u201905), pp. 363\u2013370 (2005)","DOI":"10.3115\/1219840.1219885"},{"key":"21_CR30","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. SIGKDD Explor. 11, 10\u201318 (2009)","journal-title":"SIGKDD Explor."},{"key":"21_CR31","doi-asserted-by":"crossref","unstructured":"G\u00f3mez-Adorno, H., Markov, I., Sidorov, G., Posadas-Dur\u00e1n, J., Sanchez-Perez, M.A., Chanona-Hernandez, L.: Improving feature representation based on a neural network for author profiling in social media texts. Comput. Intell. Neurosci. 2016, 13 (2016)","DOI":"10.1155\/2016\/1638936"},{"key":"21_CR32","first-page":"488","volume-title":"Lecture Notes in Computer Science","author":"Ashraf M. Kibriya","year":"2004","unstructured":"Kibriya, A.M., Frank, E., Pfahringer, B., Holmes, G.: Multinomial naive Bayes for text categorization revisited. In: Proceedings of the 17th Australian Joint Conference on Advances in Artificial Intelligence (AI\u201904), pp. 488\u2013499 (2005)"},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Sidorov, G., G\u00f3mez-Adorno, H., Markov, I., Pinto, D., Loya, N.: Computing text similarity using tree edit distance. In: Proceedings of the Annual Conference of the North American Fuzzy Information processing Society (NAFIPS\u201915) and 5th World Conference on Soft Computing, pp. 1\u20134 (2015)","DOI":"10.1109\/NAFIPS-WConSC.2015.7284129"},{"key":"21_CR34","unstructured":"Markov, I., G\u00f3mez-Adorno, H., Sidorov, G., Gelbukh, A.: Adapting cross-genre author profiling to language and corpus. In: Working Notes Papers of the CLEF 2016 Evaluation Labs. CEUR Workshop Proceedings, vol. 1609, pp. 947\u2013955. CLEF and CEUR-WS.org (2016)"}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-77116-8_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:03:11Z","timestamp":1775242991000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-77116-8_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319771151","9783319771168"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-77116-8_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"CICLing","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Linguistics and Intelligent Text Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Budapest","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 April 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 April 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicling2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cicling.org\/2017\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}