<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">mais</journal-id><journal-title-group><journal-title xml:lang="ru">Моделирование и анализ информационных систем</journal-title><trans-title-group xml:lang="en"><trans-title>Modeling and Analysis of Information Systems</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1818-1015</issn><issn pub-type="epub">2313-5417</issn><publisher><publisher-name>Yaroslavl State University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.18255/1818-1015-2020-1-48-61</article-id><article-id custom-type="elpub" pub-id-type="custom">mais-1287</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>Computing Methodologies and Applications</subject></subj-group></article-categories><title-group><article-title>Современные методы детектирования и классификации токсичных комментариев с использованием нейронных сетей</article-title><trans-title-group xml:lang="en"><trans-title>Modern Approaches to Detect and Classify Comment Toxicity Using Neural Networks</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-6652-3574</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Моржов</surname><given-names>Сeргей Владимирович</given-names></name><name name-style="western" xml:lang="en"><surname>Morzhov</surname><given-names>Sergey V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>аспирант</p></bio><bio xml:lang="en"><p>postgraduate student</p></bio><email xlink:type="simple">smorzhov@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Ярославский государственный университет им. П. Г. Демидова</institution><country>Россия</country></aff><aff xml:lang="en"><institution>P. G. Demidov Yaroslavl State University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2020</year></pub-date><pub-date pub-type="epub"><day>19</day><month>03</month><year>2020</year></pub-date><volume>27</volume><issue>1</issue><fpage>48</fpage><lpage>61</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Моржов С.В., 2020</copyright-statement><copyright-year>2020</copyright-year><copyright-holder xml:lang="ru">Моржов С.В.</copyright-holder><copyright-holder xml:lang="en">Morzhov S.V.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://www.mais-journal.ru/jour/article/view/1287">https://www.mais-journal.ru/jour/article/view/1287</self-uri><abstract><p>Рост популярности онлайн-платформ, позволяющих пользователям общаться друг с другом, делиться мнениями о различных событиях, оставлять комментарии, подтолкнул к развитию алгоритмов обработки естественного языка. Десятки миллионов сообщений в день, которые публикуют пользователи отдельно взятой социальной сети, необходимо анализировать в режиме реального времени или близко к тому с целью модерации, чтобы не допустить распространение различной противозаконной или оскорбительной информации, угроз и других видов токсичных комментариев. Разумеется такой большой объем информации может быть обработан достаточно быстро только автоматически. Возникает необходимость научить компьютер «понимать» текст, написанный человеком, что является нетривиальной задачей, пусть даже под «пониманием» текста подразумевается лишь его классификация. Бурное развитие технологий машинного обучения обусловило повсеместное внедрение новых алгоритмов. Многие задачи, в том числе и задачи обработки естественного языка, которые долгие годы считалось практически невозможно решить, сейчас вполне успешно решаются с использованием технологий глубокого обучения. В данной статье будут рассмотрены алгоритмы, построенные с использованием технологий глубокого обучения и нейронных сетей, позволяющие успешно решать задачу распознавания и классификации токсичных комментариев. Помимо этого, в статье будут приведены результаты тестирования как разработанных алгоритмов, так и ансамбля данных алгоритмов на большой обучающей выборке, собранной и размеченной специалистами компаний Google и Jigsaw.</p></abstract><trans-abstract xml:lang="en"><p>The growth of popularity of online platforms which allow users to communicate with each other, share opinions about various events, and leave comments boosted the development of natural language processing algorithms. Tens of millions of messages per day are published by users of a particular social network need to be analyzed in real time for moderation in order to prevent the spread of various illegal or offensive information, threats and other types of toxic comments. Of course, such a large amount of information can be processed quite quickly only automatically. that is why there is a need to and a way to teach computers to “understand” a text written by humans. It is a non-trivial task even if the word “understand” here means only “to classify”. the rapid evolution of machine learning technologies has led to ubiquitous implementation of new algorithms. A lot of tasks, which for many years were considered almost impossible to solve, are now quite successfully solved using deep learning technologies. this article considers algorithms built using deep learning technologies and neural networks which can successfully solve the problem of detection and classification of toxic comments. In addition, the article presents the results of the developed algorithms, as well as the results of the ensemble of all considered algorithms on a large training set collected and tagged by Google and Jigsaw.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>токчисность</kwd><kwd>обработка естественного языка</kwd><kwd>NLP</kwd><kwd>глубокое обучение</kwd><kwd>векторное представление слов</kwd><kwd>GloVe</kwd><kwd>FastText</kwd><kwd>реккурентные нейронные сети</kwd><kwd>сверточные нейронные сети</kwd><kwd>CNN</kwd><kwd>LSTM</kwd><kwd>GRU</kwd></kwd-group><kwd-group xml:lang="en"><kwd>toxicity</kwd><kwd>Natural Language Processing</kwd><kwd>NLP</kwd><kwd>deep learning</kwd><kwd>word embedding</kwd><kwd>GloVe</kwd><kwd>FastText</kwd><kwd>recurrent neural networks</kwd><kwd>convolutional neural networks</kwd><kwd>CNN</kwd><kwd>LSTM</kwd><kwd>GRU</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Toxic Comment Classification Challenge. [Online]. Available: https://www.kaggle.com/c/jigsaw-toxiccomment-classification-challenge/overview.</mixed-citation><mixed-citation xml:lang="en">Toxic Comment Classification Challenge. [Online]. Available: https://www.kaggle.com/c/jigsaw-toxiccomment-classification-challenge/overview.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">S. V. Georgakopoulos, S. K. Tasoulis, A. G. Vrahatis, and V. P. Plagianakos, “Convolutional neural networks for toxic comment classification”, in Proceedings of the 10th Hellenic Conference on Artificial Intelligence, 2018, pp. 1–6. arXiv: https://arxiv.org/pdf/1802.09957.pdf.</mixed-citation><mixed-citation xml:lang="en">S. V. Georgakopoulos, S. K. Tasoulis, A. G. Vrahatis, and V. P. Plagianakos, “Convolutional neural networks for toxic comment classification”, in Proceedings of the 10th Hellenic Conference on Artificial Intelligence, 2018, pp. 1–6. arXiv: https://arxiv.org/pdf/1802.09957.pdf.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">M. Kohli, E. Kuehler, and J. Palowitch, Paying attention to toxic comments online. [Online]. Available: https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1184/reports/6856482.pdf.</mixed-citation><mixed-citation xml:lang="en">M. Kohli, E. Kuehler, and J. Palowitch, Paying attention to toxic comments online. [Online]. Available: https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1184/reports/6856482.pdf.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">T. Chu, J. K., and M. Wang, Comment Abuse Classification with Deep Learning. [Online]. Available: https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1174/reports/2762092.pdf.</mixed-citation><mixed-citation xml:lang="en">T. Chu, J. K., and M. Wang, Comment Abuse Classification with Deep Learning. [Online]. Available: https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1174/reports/2762092.pdf.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">K. Khieu and N. N., Detecting and Classifying Toxic Comments. [Online]. Available: https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1184/reports/6837517.pdf.</mixed-citation><mixed-citation xml:lang="en">K. Khieu and N. N., Detecting and Classifying Toxic Comments. [Online]. Available: https://web.stanford.edu/class/archive/cs/cs224n/cs224n.1184/reports/6837517.pdf.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">S. Hochreiter and J. Schmidhuber, “Long short-term memory”, Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997.</mixed-citation><mixed-citation xml:lang="en">S. Hochreiter and J. Schmidhuber, “Long short-term memory”, Neural computation, vol. 9, no. 8, pp. 1735–1780, 1997.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">K. Cho, B. Van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, ¨“Learning phrase representations using RNN encoder-decoder for statistical machine translation”, arXiv preprint arXiv:1406.1078, 2014.</mixed-citation><mixed-citation xml:lang="en">K. Cho, B. Van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, ¨“Learning phrase representations using RNN encoder-decoder for statistical machine translation”, arXiv preprint arXiv:1406.1078, 2014.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">J. Pennington, R. Socher, and C. Manning, “Glove: Global vectors for word representation”, in Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 2014, pp. 1532–1543.</mixed-citation><mixed-citation xml:lang="en">J. Pennington, R. Socher, and C. Manning, “Glove: Global vectors for word representation”, in Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 2014, pp. 1532–1543.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">A. Joulin, E. Grave, P. Bojanowski, and T. Mikolov, “Bag of tricks for efficient text classification”, Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, vol. 2, pp. 427–431, 2017.</mixed-citation><mixed-citation xml:lang="en">A. Joulin, E. Grave, P. Bojanowski, and T. Mikolov, “Bag of tricks for efficient text classification”, Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, vol. 2, pp. 427–431, 2017.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, “Empirical evaluation of gated recurrent neural networks on sequence modeling”, arXiv preprint arXiv:1412.3555, 2014.</mixed-citation><mixed-citation xml:lang="en">J. Chung, C. Gulcehre, K. Cho, and Y. Bengio, “Empirical evaluation of gated recurrent neural networks on sequence modeling”, arXiv preprint arXiv:1412.3555, 2014.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate”, arXiv preprint arXiv:1409.0473, 2014.</mixed-citation><mixed-citation xml:lang="en">D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate”, arXiv preprint arXiv:1409.0473, 2014.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Z. Yang, D. Yang, C. Dyer, X. He, A. Smola, and E. Hovy, “Hierarchical attention networks for document classification”, in Proceedings of NAACL-HLT, 2016, pp. 1480–1489. [Online]. Available: hps://www.cs.cmu.edu/%5C%20./hovy/papers/16HLT-hierarchical-attention-networks.pdf.</mixed-citation><mixed-citation xml:lang="en">Z. Yang, D. Yang, C. Dyer, X. He, A. Smola, and E. Hovy, “Hierarchical attention networks for document classification”, in Proceedings of NAACL-HLT, 2016, pp. 1480–1489. [Online]. Available: hps://www.cs.cmu.edu/%5C%20./hovy/papers/16HLT-hierarchical-attention-networks.pdf.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">M. Hughes, I. Li, S. Kotoulas, and T. Suzumura, “Medical text classification using convolutional neural networks”, Stud Health Technol Inform, vol. 235, pp. 246–50, 2017.</mixed-citation><mixed-citation xml:lang="en">M. Hughes, I. Li, S. Kotoulas, and T. Suzumura, “Medical text classification using convolutional neural networks”, Stud Health Technol Inform, vol. 235, pp. 246–50, 2017.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">K. Kowsari, K. Jafari Meimandi, M. Heidarysafa, S. Mendu, L. Barnes, and D. Brown, “Text classification algorithms: A survey”, Information, vol. 10, no. 4, p. 150, 2019.</mixed-citation><mixed-citation xml:lang="en">K. Kowsari, K. Jafari Meimandi, M. Heidarysafa, S. Mendu, L. Barnes, and D. Brown, “Text classification algorithms: A survey”, Information, vol. 10, no. 4, p. 150, 2019.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
