{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T06:23:55Z","timestamp":1777703035829,"version":"3.51.4"},"reference-count":40,"publisher":"SAGE Publications","issue":"5","license":[{"start":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T00:00:00Z","timestamp":1557792000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2019,5,14]]},"abstract":"<jats:p>\n                    We present a method for gender and language variety identification using a convolutional neural network (CNN). We compare the performance of this method with a traditional machine learning algorithm \u2013 support vector machines (SVM) trained on character n-grams (\n                    <jats:italic>n<\/jats:italic>\n                    \u00a0=\u00a03\u20138) and lexical features (unigrams and bigrams of words), and their combinations. We use a single multi-labeled corpus composed of news articles in different varieties of Spanish developed specifically for these tasks. We present a convolutional neural network trained on word- and sentence-level embeddings architecture that can be successfully applied to gender and language variety identification on a relatively small corpus (less than 10,000 documents). Our experiments show that the deep learning approach outperforms a traditional machine learning approach on both tasks, when named entities are present in the corpus. However, when evaluating the performance of these approaches reducing all named entities to a single symbol \u201cNE\u201d to avoid topic-dependent features, the drop in accuracy is higher for the deep learning approach.\n                  <\/jats:p>","DOI":"10.3233\/jifs-179032","type":"journal-article","created":{"date-parts":[[2019,5,14]],"date-time":"2019-05-14T12:06:43Z","timestamp":1557835603000},"page":"4845-4855","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":7,"title":["A convolutional neural network approach for gender and language variety identification"],"prefix":"10.1177","volume":"36","author":[{"given":"Helena","family":"G\u00f3mez-Adorno","sequence":"first","affiliation":[{"name":"Instituto de Investigaciones en Matem\u00e1ticas Aplicadas y en Sistemas (IIMAS), Universidad Nacional Aut\u00f3noma de M\u00e9xico, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roddy","family":"Fuentes-Alba","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilia","family":"Markov","sequence":"additional","affiliation":[{"name":"Institut National de Recherche en Informatique et en Automatique (INRIA), France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grigori","family":"Sidorov","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Gelbukh","sequence":"additional","affiliation":[{"name":"Centro de Investigaci\u00f3n en Computaci\u00f3n (CIC), Instituto Polit\u00e9cnico Nacional, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2019,5,14]]},"reference":[{"key":"e_1_3_3_2_2","author":"Rangel F.","year":"2017","unstructured":"RangelF., RossoP., PotthastM. and SteinB., Overview of the 5th Author Profiling Task at PAN 2017: Gender and Language Variety Identification in Twitter, in: Working Notes Papers of the CLEF 2017 Evaluation Labs, CEUR-WS.org, 2017.","journal-title":"Working Notes Papers of the CLEF 2017 Evaluation Labs"},{"key":"e_1_3_3_3_2","first-page":"1","author":"Rangel F.","year":"2016","unstructured":"RangelF., RossoP., VerhoevenB., DaelemansW., PotthastM. and SteinB., Overview of the 4th Author Profiling Task at PAN 2016: Cross-genre Evaluations, in: Working Notes Papers of the CLEF 2016 Evaluation Labs, CEUR-WS.org, 2016, pp. 1\u201326 .","journal-title":"Working Notes Papers of the CLEF 2016 Evaluation Labs"},{"key":"e_1_3_3_4_2","first-page":"15","author":"\u00c7\u00f6ltekin C.","year":"2016","unstructured":"\u00c7\u00f6ltekinC. and RamaT., Discriminating similar languages: Experiments with linear SVMs and neural networks, in: Proceedings of the 3rd Workshop on NLP for Similar Languages, Varieties and Dialects, VarDial\u201916, 2016, pp. 15\u201324.","journal-title":"Proceedings of the 3rd Workshop on NLP for Similar Languages, Varieties and Dialects, VarDial\u201916"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-1217"},{"key":"e_1_3_3_6_2","first-page":"145","author":"Sanchez-Perez M.A.","year":"2017","unstructured":"Sanchez-PerezM.A., MarkovI., G\u00f3mez-AdornoH. and SidorovG., Comparison of Character n-grams and Lexical Features on Author, Gender, and Language Variety Identification on the Same Spanish News Corpus, in: International Conference of the Cross-Language Evaluation Forum for European Languages, CLEF\u201917, Springer, 2017, pp. 145\u2013151.","journal-title":"International Conference of the Cross-Language Evaluation Forum for European Languages"},{"key":"e_1_3_3_7_2","first-page":"20","author":"Markov I.","year":"2017","unstructured":"MarkovI., G\u00f3mez-AdornoH., SidorovG. and GelbukhA., The Winning Approach to Cross-Genre Gender Identification in Russian at Rusprofiling 2017, in: FIRE 2017 Working Notes, FIRE\u201917, 2017, pp. 20\u201324.","journal-title":"FIRE 2017 Working Notes, FIRE\u201917"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"e_1_3_3_9_2","first-page":"655","author":"Blunsom P.","year":"2014","unstructured":"BlunsomP., GrefenstetteE. and KalchbrennerN., A convolutional neural network for modelling sentences, in: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL, 2014, pp. 655\u2013665.","journal-title":"Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, ACL"},{"issue":"4","key":"e_1_3_3_10_2","first-page":"759","article-title":"Hybrid attention networks for chinese short text classification","volume":"21","author":"Zhou Y.","year":"2017","unstructured":"ZhouY., XuJ., CaoJ., XuB., LiC. and XuB., Hybrid attention networks for chinese short text classification, Computaci\u00f3n y Sistemas21(4) (2017), 759\u2013769.","journal-title":"Computaci\u00f3n y Sistemas"},{"issue":"4","key":"e_1_3_3_11_2","article-title":"EDGE2VEC: Edge representations for large-scale scalable hierarchical learning","volume":"21","author":"Sohrab M.G.","year":"2017","unstructured":"SohrabM.G., NakataT., MiwaM. and SasakiY., EDGE2VEC: Edge representations for large-scale scalable hierarchical learning, Computaci\u00f3n y Sistemas21(4) (2017).","journal-title":"Computaci\u00f3n y Sistemas"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2017.23"},{"key":"e_1_3_3_13_2","article-title":"Character-level and multi-channel convolutional neural networks for largescale authorship attribution","author":"Ruder S.","year":"2016","unstructured":"RuderS., GhaffariP. and BreslinJ.G., Character-level and multi-channel convolutional neural networks for largescale authorship attribution, arXiv preprint arXiv:1609.06686 (2016).","journal-title":"arXiv preprint arXiv:1609.06686"},{"key":"e_1_3_3_14_2","first-page":"1","author":"Zampieri M.","year":"2017","unstructured":"ZampieriM., MalmasiS., Ljube\u0161i\u0107N., NakovP., AliA., TiedemannJ., ScherrerY. and AepliN., Findings of the Var-Dial Evaluation Campaign 2017, in: Proceedings of the 4th Workshop on NLP for Similar Languages, Varieties and Dialects, VarDial\u201917, 2017, pp. 1\u201315.","journal-title":"Proceedings of the 4th Workshop on NLP for Similar Languages, Varieties and Dialects, VarDial\u201917"},{"key":"e_1_3_3_15_2","first-page":"1","author":"Zampieri M.","year":"2015","unstructured":"ZampieriM., TanL., Ljube\u0161i\u0107N., TiedemannJ. and NakovP., Overview of the DSL shared task 2015, in: Proceedings of the Joint Workshop on Language Technology for Closely Related Languages, Varieties and Dialects, LT4VarDial\u201915, 2015, pp. 1\u20139.","journal-title":"Proceedings of the Joint Workshop on Language Technology for Closely Related Languages, Varieties and Dialects, LT4VarDial\u201915"},{"key":"e_1_3_3_16_2","author":"R\u00edos G.","year":"2017","unstructured":"R\u00edosG., SidorovG., CastroN., NavaA. and Chanona-Hern\u00e1ndezL., Relevance of Named Entities in Authorship Attribution, in: Proceedings of the 15th Mexican International Conference on Artificial Intelligence (MICAI\u201916), LNAI, Springer, 2017.","journal-title":"Proceedings of the 15th Mexican International Conference on Artificial Intelligence (MICAI\u201916), LNAI"},{"key":"e_1_3_3_17_2","first-page":"1","volume":"1391","author":"Rangel F.","year":"2015","unstructured":"RangelF., CelliF., RossoP., PottastM., SteinB. and DaelemansW., Overview of the 3rd Author Profiling Task at PAN 2015, in: CLEF 2015 Labs and Workshops, Notebook Papers, Vol. 1391, CEUR.org, 2015, pp. 1\u201318.","journal-title":"CLEF 2015 Labs and Workshops, Notebook Papers"},{"key":"e_1_3_3_18_2","volume":"1391","author":"\u00c1lvarez-Carmona M.A.","year":"2015","unstructured":"\u00c1lvarez-CarmonaM.A., L\u00f3pez-MonroyA.P., Montes-y-G\u00f3mezM., Villase\u00f1or-PinedaL. and Jair-EscalanteH., INAOE\u2019s Participation at PAN\u201915: Author Profiling task, in: Working Notes Papers of the CLEF 2015 Evaluation Labs, Vol. 1391, CEUR.org, 2015.","journal-title":"Working Notes Papers of the CLEF 2015 Evaluation Labs"},{"key":"e_1_3_3_19_2","first-page":"7","author":"Gencheva P.","year":"2016","unstructured":"GenchevaP., BoyanovM., DenevaE., NakovP., GeorgievG., KiprovY. and KoychevI., PANcakes Team: A Composite System of Genre-Agnostic Features For Author Profiling, in: Working Notes Papers of the CLEF 2016 Evaluation Labs, CEUR-WS.org, 2016, p. 7.","journal-title":"Working Notes Papers of the CLEF 2016 Evaluation Labs"},{"key":"e_1_3_3_20_2","first-page":"1","author":"Malmasi S.","year":"2016","unstructured":"MalmasiS., ZampieriM., Ljube\u0161i\u0107N., NakovP., AliA. and TiedemannJ., Discriminating between Similar Languages and Arabic Dialect Identification: A Report on the 3rd DSL shared task, in: Proceedings of the 3rd Workshop on Language Technology for Closely Related Languages, Varieties and Dialects, VarDial\u201916, 2016, pp. 1\u201314.","journal-title":"Proceedings of the 3rd Workshop on Language Technology for Closely Related Languages, Varieties and Dialects, VarDial\u201916"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-1214"},{"key":"e_1_3_3_22_2","article-title":"Author Profiling with Word+Character Neural Attention Network","author":"Miura Y.","year":"2017","unstructured":"MiuraY., TaniguchiT., TaniguchiM. and OhkumaT., Author Profiling with Word+Character Neural Attention Network, in: CLEF 2017 Evaluation Labs and Workshop \u2013 Working Notes Papers, CEUR-WS.org, 2017.","journal-title":"CLEF 2017 Evaluation Labs and Workshop \u2013 Working Notes Papers"},{"key":"e_1_3_3_23_2","article-title":"Convolutional Neural Networks for Author Profiling in PAN 2017","author":"Sierra S.","year":"2017","unstructured":"SierraS., Montes-Y-G\u00f3mezM., SolorioT. and Gonz\u00e1lezF., Convolutional Neural Networks for Author Profiling in PAN 2017, in: CLEF 2017 Evaluation Labs and Workshop \u2013 Working Notes Papers, CEUR-WS.org, 2017.","journal-title":"CLEF 2017 Evaluation Labs and Workshop \u2013 Working Notes Papers"},{"key":"e_1_3_3_24_2","article-title":"Author Profiling with Bidirectional RNNs using Attention with GRUs","author":"Kodiyan D.","year":"2017","unstructured":"KodiyanD., HardeggerF., NeuhausS. and CieliebakM., Author Profiling with Bidirectional RNNs using Attention with GRUs, in: CLEF 2017 Evaluation Labs and Workshop \u2013 Working Notes Papers, CEUR-WS.org, 2017.","journal-title":"CLEF 2017 Evaluation Labs and Workshop \u2013 Working Notes Papers"},{"key":"e_1_3_3_25_2","first-page":"93","author":"Sapkota U.","year":"2015","unstructured":"SapkotaU., BethardS., Montes-y-G\u00f3mezM. and SolorioT., 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, 2015, pp. 93\u2013102.","journal-title":"Proceedings of the 2015 Annual Conference of the North American Chapter of the ACL: Human Language Technologies, NAACL-HLT\u201915"},{"key":"e_1_3_3_26_2","first-page":"117","volume":"10062","author":"Markov I.","year":"2017","unstructured":"MarkovI., G\u00f3mez-AdornoH., Posadas-Dur\u00e1nJ., SidorovG. and GelbukhA., Author Profiling with doc2vec Neural Network-based Document Embeddings, in: Proceedings of the 15th Mexican International Conference on Artificial Intelligence, MICAI 2016, Vol. 10062, LNAI, Springer, 2017, pp. 117\u2013131.","journal-title":"Proceedings of the 15th Mexican International Conference on Artificial Intelligence, MICAI 2016"},{"issue":"2","key":"e_1_3_3_27_2","first-page":"427","article-title":"On the robustness of authorship attribution based on character n-gram features","volume":"21","author":"Stamatatos E.","year":"2013","unstructured":"StamatatosE., On the robustness of authorship attribution based on character n-gram features, Journal of Law & Policy21(2) (2013), 427\u2013439.","journal-title":"Journal of Law & Policy"},{"issue":"2","key":"e_1_3_3_28_2","first-page":"279","article-title":"Detecci\u00f3n autom\u00e1tica de similitud entre programas del lenguaje de programaci\u00f3n karel basada en t\u00e9cnicas de procesamiento de lenguaje natural","volume":"20","author":"Sidorov G.","year":"2016","unstructured":"SidorovG., Ibarra RomeroM., MarkovI., Guzman-CabreraR., Chanona-Hern\u00e1ndezL. and Vel\u00e1squezF., Detecci\u00f3n autom\u00e1tica de similitud entre programas del lenguaje de programaci\u00f3n karel basada en t\u00e9cnicas de procesamiento de lenguaje natural, Computaci\u00f3n y Sistemas20(2) (2016), 279\u2013288.","journal-title":"Computaci\u00f3n y Sistemas"},{"issue":"2","key":"e_1_3_3_29_2","article-title":"Improving the boilerpipe algorithm for boilerplate removal in news articles using HTML tree structure","volume":"22","author":"Jim\u00e9nez F.V.","year":"2018","unstructured":"Jim\u00e9nezF.V., S\u00e1nchez-P\u00e9rezM.A., G\u00f3mez-AdornoH., Posadas-Dur\u00e1nJ.P., SidorovG. and GelbukhA.F., Improving the boilerpipe algorithm for boilerplate removal in news articles using HTML tree structure, Computaci\u00f3n y Sistemas22(2) (2018).","journal-title":"Computaci\u00f3n y Sistemas"},{"key":"e_1_3_3_30_2","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","volume":"9","author":"Fan R.-E.","year":"2008","unstructured":"FanR.-E., ChangK.-W., HsiehC.-J., WangX.-R. and LinC.-J., LIBLINEAR: A library for large linear classification, Journal of Machine Learning Research9 (2008), 1871\u20131874.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013637720281"},{"key":"e_1_3_3_32_2","author":"Witten I.","year":"2016","unstructured":"WittenI., FrankE., HallM., PalC., Data Mining: Practical Machine Learning Tools and Techniques, 4th edn, Morgan Kaufmann, 2016.","journal-title":"Data Mining: Practical Machine Learning Tools and Techniques, 4th edn"},{"key":"e_1_3_3_33_2","first-page":"384","author":"Turian J.","year":"2010","unstructured":"TurianJ., RatinovL. and BengioY., Word representations: A simple and general method for semisupervised learning, in: Proceedings of the 48thAnnual Meeting of the Association for Computational Linguistics, 2010, pp. 384\u2013394.","journal-title":"Proceedings of the 48thAnnual Meeting of the Association for Computational Linguistics"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"e_1_3_3_35_2","first-page":"1","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov T.","year":"2013","unstructured":"MikolovT., ChenK., CorradoG. and DeanJ., Efficient estimation of word representations in vector space, arXiv preprint arXiv:1301.3781 (2013), 1\u201312.","journal-title":"arXiv preprint arXiv:1301.3781"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"e_1_3_3_37_2","first-page":"1188","author":"Le Q.V.","year":"2014","unstructured":"LeQ.V. and MikolovT., Distributed Representations of Sentences and Documents, in: International Conference on Machine Learning, 2014, pp. 1188\u20131196.","journal-title":"International Conference on Machine Learning"},{"key":"e_1_3_3_38_2","first-page":"1","article-title":"Document embeddings learned on various types of n-grams for cross-topic authorship attribution","author":"G\u00f3mez-Adorno H.","year":"2018","unstructured":"G\u00f3mez-AdornoH., Posadas-Dur\u00e1nJ.-P., SidorovG. and PintoD., Document embeddings learned on various types of n-grams for cross-topic authorship attribution, Computing (2018), 1\u201316.","journal-title":"Computing"},{"key":"e_1_3_3_39_2","article-title":"ADADELTA: An adaptive learning rate method","author":"Zeiler M.D.","year":"2012","unstructured":"ZeilerM.D., ADADELTA: An adaptive learning rate method, arXiv preprint arXiv:1212.5701 (2012).","journal-title":"arXiv preprint arXiv:1212.5701"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219885"},{"key":"e_1_3_3_41_2","article-title":"Language- and Subtask-Dependent Feature Selection and Classifier Parameter Tuning for Author Profiling","author":"Markov I.","year":"2017","unstructured":"MarkovI., G\u00f3mez-AdornoH. and SidorovG., Language- and Subtask-Dependent Feature Selection and Classifier Parameter Tuning for Author Profiling, in: CLEF 2017 Evaluation Labs and Workshop \u2013 Working Notes Papers, Dublin, Ireland, CEUR-WS.org, 2017.","journal-title":"CLEF 2017 Evaluation Labs and Workshop \u2013 Working Notes Papers"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-179032","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-179032","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-179032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:37:40Z","timestamp":1777455460000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-179032"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,14]]},"references-count":40,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2019,5,14]]}},"alternative-id":["10.3233\/JIFS-179032"],"URL":"https:\/\/doi.org\/10.3233\/jifs-179032","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,14]]}}}