<?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">dgisocio</journal-id><journal-title-group><journal-title xml:lang="ru">Цифровая социология/Digital Sociology</journal-title><trans-title-group xml:lang="en"><trans-title>Digital Sociology</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2658-347X</issn><issn pub-type="epub">2713-1653</issn><publisher><publisher-name>Государственный университет управления</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.26425/2658-347X-2024-7-3-42-52</article-id><article-id custom-type="elpub" pub-id-type="custom">dgisocio-327</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>ЦИФРОВАЯ СРЕДА</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>DIGITAL ENVIRONMENT</subject></subj-group></article-categories><title-group><article-title>Автоматизация выявления заказных отзывов на маркетплейсах при помощи экспертных признаков и реакций покупателей</article-title><trans-title-group xml:lang="en"><trans-title>Automatic detection of fake reviews at marketplaces using expert-based features and consumers’ reactions</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0009-1336-1415</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Бородулина</surname><given-names>А. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Borodulina</surname><given-names>A. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Бородулина Анастасия Николаевна, Магистр</p><p>Тюмень</p></bio><bio xml:lang="en"><p>Anastasiya N. Borodulina, Postgraduate Student</p><p>Tyumen</p></bio><email xlink:type="simple">borannik@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-0781-8633</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Михалькова</surname><given-names>Е. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Mikhalkova</surname><given-names>E. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Михалькова Елена Владимировна, Доц. каф. информационных технологий в научной проектнойдеятельности</p><p>Санкт-Петербург</p><p> </p></bio><bio xml:lang="en"><p>Elena V. Mikhalkova, Associate Professor at the Information Technology in Scientific Project Activities Department</p><p>St. Petersburg</p></bio><email xlink:type="simple">e.mikhalkova@eu.spb.ru</email><xref ref-type="aff" rid="aff-2"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Тюменский государственный университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Tyumen State University</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Европейский университет в Санкт-Петербурге</institution><country>Россия</country></aff><aff xml:lang="en"><institution>European University at St. Petersburg</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2024</year></pub-date><pub-date pub-type="epub"><day>20</day><month>10</month><year>2024</year></pub-date><volume>7</volume><issue>3</issue><fpage>42</fpage><lpage>52</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Бородулина А.Н., Михалькова Е.В., 2024</copyright-statement><copyright-year>2024</copyright-year><copyright-holder xml:lang="ru">Бородулина А.Н., Михалькова Е.В.</copyright-holder><copyright-holder xml:lang="en">Borodulina A.N., Mikhalkova E.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://digitalsociology.guu.ru/jour/article/view/327">https://digitalsociology.guu.ru/jour/article/view/327</self-uri><abstract><p>Авторы представляют практическое исследование особенностей заказных отзывов, которые упоминаются маркетологами и другими экспертами. Из-за обилия заказных отзывов на маркетплейсах доверие потребителей падает не просто к продавцу или площадке, но к самому жанру. В работе представлены результаты автоматической классификации отзывов с российских маркетплейсов на потенциально заказные и честные при помощи моделирования признаков, которые эксперты называют признаками заказного отзыва (наличие шаблонных слов, восклицательных знаков, эмодзи, положительная тональность), и алгоритмов машинного обучения. Для решения поставленной задачи был собран корпус с российских маркетплейсов Wildberries и «Мегамаркет» объемом 6 288 текстов. В качестве целевой переменной (предсказываемого класса) выступает соотношение лайков и дизлайков, поставленных отзыву другими покупателями. Лучший результат демонстрирует метод опорных векторов SVM (англ. support vector machine) в бинарной классификации на отзывы с низким и высоким рейтингом (без нейтральных). Модель классификации подтверждает, что формальные признаки, выделяемые экспертами как указывающие на заказные отзывы, действительно имеют предсказательный потенциал. Качество модели снижают дисбаланс в классах и недостаточное количество отзывов с реакциями покупателей в нашем корпусе, что оставляет задел для дальнейшей работы.</p></abstract><trans-abstract xml:lang="en"><p>The article presents the results of a practical study of the features of fake reviews that are described by marketers and other experts. Due to the abundance of fake reviews on marketplaces, consumer trust falls not only in the seller or platform, but in the genre itself. The paper presents the results of automatic classification of reviews from Russian marketplaces into potentially fake and honest ones using modelling of features that experts call labels of a fake review (presence of template words, exclamation marks, emoji, positive sentiment), and machine learning algorithms. To solve the problem, a corpus of 6 288 texts from the Russian marketplaces Wildberries and Megamarket has been collected. The target variable (predicted class) is the ratio of likes and dislikes given to the review by other buyers. The best result is demonstrated by the support vector machine algorithm in binary classification into reviews with a low and high ratings (without neutral ones). The classification model confirms that the formal features identified by experts as indicating fake reviews indeed have predictive potential. The quality of the model is reduced by the imbalance in classes and insufficient number of reviews with buyer reactions in our corpus, which leaves room for further work.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>Заказной отзыв</kwd><kwd>маркетплейс</kwd><kwd>доверие потребителей</kwd><kwd>анализ данных</kwd><kwd>моделирование признаков</kwd><kwd>компьютерная лингвистика</kwd><kwd>машинное обучение</kwd><kwd>метод опорных векторов</kwd><kwd>бинарная классификация</kwd></kwd-group><kwd-group xml:lang="en"><kwd>Fake review</kwd><kwd>marketplace</kwd><kwd>consumer trust</kwd><kwd>data analysis</kwd><kwd>feature modelling</kwd><kwd>computational linguistics</kwd><kwd>machine learning</kwd><kwd>SVM</kwd><kwd>binary classification</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">Ахмаева Л.Г. Влияние возрастной и гендерной специфики пользователей социальных сетей в России на методы маркетинга и рекламы. Цифровая социология. 2020;3(3):21–28. http://doi.org/10.26425/2658-347X-2020-3-3-21-28</mixed-citation><mixed-citation xml:lang="en">Akhmaeva L.G. Influence of age and gender specifics of social network users in Russia on marketing and advertising methods. Digital Sociology. 2020;3(3):21–28. (In Russian). http://doi.org/10.26425/2658-347X-2020-3-3-21-28</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Величко И.Ф., Леонова Л.И. Отзыв на товар как тип текста (на примере популярного интернет-магазина). В кн.: Исследования молодых ученых: материалы студенческой международной научно-практической конференции, Курск, 12 апреля 2022 г. Курск: Курский институт кооперации (филиал) Белгородского университета кооперации, экономики и права; 2022. С. 123–127.</mixed-citation><mixed-citation xml:lang="en">Bulchand-Gidumal J., Melián-González S. Fighting fake reviews with blockchain-enabled consumer-generated reviews. Current Issues in Tourism. 2024;5(27):739–753.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Назаров Д.М. О влиянии отзывов потребителей в интернете на решения о покупке. Столыпинский вестник. 2022;7(4):3728–3735.</mixed-citation><mixed-citation xml:lang="en">Fiallos A., Anton E. Towards reliable app marketplaces: machine learning-based detection of fraudulent reviews: Proceedings of the 7th International Conference on Applied Informatics, October 24–26, Viña del Mar, 2024. Cham: Springer; 2024. Pp. 229–242.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Юдалевич Н.В. К вопросу о важности предоставления отзывов при покупках на маркетплейсах. Бизнес-образование в экономике знаний. 2023;2(25):67–72.</mixed-citation><mixed-citation xml:lang="en">Iudalevich N.V. To the question of the importance of providing reviews when purchasing on marketplaces. Business education in the knowledge economy. 2023;2(25):67–72. (In Russian).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Bulchand-Gidumal J., Melián-González S. Fighting fake reviews with blockchain-enabled consumer-generated reviews. Current Issues in Tourism. 2024;5(27):739–753.</mixed-citation><mixed-citation xml:lang="en">Kim J.M., Park K.K., Mariani M., Wamba S.F. Investigating reviewers’ intentions to post fake vs. authentic reviews based on behavioral linguistic features. Technological forecasting and social change. 2024;198:122971. http://dx.doi.org/10.1016/j.techfore.2023.122971</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Fiallos A., Anton E. Towards reliable app marketplaces: machine learning-based detection of fraudulent reviews: Proceedings of the 7th International Conference on Applied Informatics, October 24–26, Viña del Mar, 2024. Cham: Springer; 2024. Pp. 229–242.</mixed-citation><mixed-citation xml:lang="en">Krishnaiah K.R. Predicting fake online reviews: a comprehensive study of supervised and semi-supervised learning models. Turkish journal of computer and mathematics education (TURCOMAT). 2023;3(14):392–399.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Kim J.M., Park K.K., Mariani M., Wamba S.F. Investigating reviewers’ intentions to post fake vs. authentic reviews based on behavioral linguistic features. Technological forecasting and social change. 2024;198:122971. http://dx.doi.org/10.1016/j.techfore.2023.122971</mixed-citation><mixed-citation xml:lang="en">Malik A.Z., Sadeghi K.R., Paswan A., Kanwal F. Incentivized fake reviews: when cognitive reappraisal paves the way for an immoral journey. Journal of Consumer Behaviour. 2024;4(23):1962–1978. https://doi.org/10.1002/cb.2315</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Krishnaiah K.R. Predicting fake online reviews: a comprehensive study of supervised and semi-supervised learning models. Turkish journal of computer and mathematics education (TURCOMAT). 2023;3(14):392–399.</mixed-citation><mixed-citation xml:lang="en">Nazarov D.M. On the impact of online consumer reviews on purchasing decisions. Stolypin vestnik. 2022;7(4):3728–3735. (In Russian).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Malik A.Z., Sadeghi K.R., Paswan A., Kanwal F. Incentivized fake reviews: when cognitive reappraisal paves the way for an immoral journey. Journal of Consumer Behaviour. 2024;4(23):1962–1978. https://doi.org/10.1002/cb.2315</mixed-citation><mixed-citation xml:lang="en">Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O. et al. Scikit-learn: machine learning in Python. Journal of Machine Learning Research.2011;12:2825–2830.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O. et al. Scikit-learn: machine learning in Python. Journal of Machine Learning Research.2011;12:2825–2830.</mixed-citation><mixed-citation xml:lang="en">Rogers A., Romanov A., Rumshisky A., Volkova S., Gronas M., Gribov A. Rusentiment: an enriched sentiment analysis dataset for social media in Russian: Proceedings of the 27th International Conference on Computational Linguistics. Santa Fe: Association for Computational Linguistics; 2018. Pp. 755–763.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Rogers A., Romanov A., Rumshisky A., Volkova S., Gronas M., Gribov A. Rusentiment: an enriched sentiment analysis dataset for social media in Russian: Proceedings of the 27th International Conference on Computational Linguistics. Santa Fe: Association for Computational Linguistics; 2018. Pp. 755–763.</mixed-citation><mixed-citation xml:lang="en">Shukla A.D., Goh J.M. Fighting fake reviews: authenticated anonymous reviews using identity verification. Business Horizons. 2024;1(67):71–81.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Shukla A.D., Goh J.M. Fighting fake reviews: authenticated anonymous reviews using identity verification. Business Horizons. 2024;1(67):71–81.</mixed-citation><mixed-citation xml:lang="en">Thao L.Q., Kien D.T., Thuy D.T.T., Thuy L.T.M., Bach N.Ch., Duc T.T. et al. Designing a deep learning-based application for detecting fake online reviews. Engineering Applications of Artificial Intelligence. 2024;134:108708. https://doi.org/10.1016/j.engappai.2024.108708</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Thao L.Q., Kien D.T., Thuy D.T.T., Thuy L.T.M., Bach N.Ch., Duc T.T. et al. Designing a deep learning-based application for detecting fake online reviews. Engineering Applications of Artificial Intelligence. 2024;134:108708. https://doi.org/10.1016/j.engappai.2024.108708</mixed-citation><mixed-citation xml:lang="en">Velichko I.F., Leonova L.I. Product review as a type of text (on the example of a popular online store). In: Research of young scientists: Proceedings of the Student International Scientific and Practical Conference, Kursk, April 12, 2022. Kursk: Kursk Cooperative Institute (Branch) of the Belgorod University of Cooperation, Economics, and Law; 2022. Pp. 123–127. (In Russian).</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>
