<?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">lingngu</journal-id><journal-title-group><journal-title xml:lang="ru">Вестник НГУ. Серия: Лингвистика и межкультурная коммуникация</journal-title><trans-title-group xml:lang="en"><trans-title>NSU Vestnik. Series: Linguistics and Intercultural Communication</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1818-7935</issn><publisher><publisher-name>Новосибирский государственный университет</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.25205/1818-7935-2022-20-4-90-106</article-id><article-id custom-type="elpub" pub-id-type="custom">lingngu-470</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>ПРИКЛАДНАЯ ЛИНГВИСТИКА</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>APPLIED LINGUISTICS</subject></subj-group></article-categories><title-group><article-title>Об одном подходе к автоматической суммаризации потребительских отзывов</article-title><trans-title-group xml:lang="en"><trans-title>An Approach to Summarizing Product Reviews</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-1987-0244</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Чечнева</surname><given-names>Н. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Chechneva</surname><given-names>N. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Чечнева Надежда Сергеевна, аспирант</p><p>Санкт-Петербург</p></bio><bio xml:lang="en"><p>Nadezhda S. Chechneva, PhD student</p><p>Saint Petersburg</p></bio><email xlink:type="simple">chechnevanadegda@mail.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Санкт-Петербургский государственный университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Saint Petersburg State University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2022</year></pub-date><pub-date pub-type="epub"><day>05</day><month>02</month><year>2023</year></pub-date><volume>20</volume><issue>4</issue><fpage>90</fpage><lpage>106</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Чечнева Н.С., 2023</copyright-statement><copyright-year>2023</copyright-year><copyright-holder xml:lang="ru">Чечнева Н.С.</copyright-holder><copyright-holder xml:lang="en">Chechneva N.S.</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://lingngu.elpub.ru/jour/article/view/470">https://lingngu.elpub.ru/jour/article/view/470</self-uri><abstract><p>Потребительские отзывы являются важным аспектом электронной коммерции, они влияют на коммуникативное поведение потенциального адресата (покупателей). Пользователи часто читают их, чтобы получить общее либо конкретное представление о продукте или услуге. Компании анализируют отзывы клиентов для усовершенствования своих продуктов и/или для корректировки маркетинговой стратегии. Однако из-за слабой структурированности отзывов и быстро возрастающего количества, их изучение становится трудоемким процессом как для пользователей, так и для компаний. Вследствие этого повышается актуальность проблемы автоматической суммаризации потребительских отзывов. В данной статье предлагается новый подход к решению этой задачи, разработанный на основе проведенного и апробированного исследования отзывов о цифровой и бытовой технике. Он позволяет структурировать и расположить тексты отзывов в соответствии с тематической иерархией аспектов, предоставить сводную информацию об их тональности (количестве положительных и отрицательных упоминаний тех или иных аспектов), а также показать наиболее релевантные предложения. Исследование строится на материале текстов отзывов, собранных с интернет-ресурса «Яндекс.Маркет». Подробно описан процесс суммаризации отзывов, включающий несколько этапов: 1) экспертное формирование перечня тематических классов аспектных терминов; 2) классификация предложений по заданным классам аспектов; 3) распределение предложений на два класса – положительные и отрицательные – с подсчетом количества положительных и отрицательных предложений внутри каждого класса аспектов; 4) этап ранжирования предложений; 5) этап визуализации результатов, полученных на предыдущих шагах. Качество работы алгоритма по созданию резюме из большой коллекции отзывов было протестировано на пяти моделях товаров из следующих категорий: кофемашины, роботы-пылесосы, электронные книги, телевизоры, стиральные машины.</p></abstract><trans-abstract xml:lang="en"><p>Product reviews are an important feature of e-commerce because they influence the communicative behavior of a potential addressee (customers). Users often read online product reviews to get either general or specific information about a product or service. Besides, companies analyze customer reviews to improve their product quality or to adjust their marketing strategy. However, many reviews are unstructured and long. With the number of product reviews growing rapidly, reading a large number of reviews becomes a time-consuming process for both users and companies. Therefore, review summarization becomes a serious issue. In this paper, we propose a new approach to summarizing reviews of electronics and household appliances. The proposed approach makes it possible to structure information for every aspect category; it provides calculation sentiment score for each aspect category, and shows the most relevant sentences for each aspect. We used product reviews from Yandex.Market as target data. Our task was performed in five main phases: 1) expert identification of thematic aspect categories; 2) classifying sentences into the predefined aspect categories; 3) sentence classification into two classes—positive and negative—with calculating the number of both type sentences within each aspect category; 4) sentence ranking; 5) visualization of the results obtained in the previous phases. The quality of the algorithm for creating a resume from a large collection of reviews has been tested on five models of products from the following categories: coffee machines, robot vacuum cleaners, e-books, TV-sets, and washing machines.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>компьютерная лингвистика</kwd><kwd>машинное обучение</kwd><kwd>суммаризация отзывов</kwd><kwd>анализ тональности</kwd><kwd>векторизация предложений</kwd><kwd>ранжирование предложений</kwd></kwd-group><kwd-group xml:lang="en"><kwd>computational linguistics</kwd><kwd>machine learning</kwd><kwd>review summarization</kwd><kwd>sentiment analysis</kwd><kwd>sentence embeddings</kwd><kwd>sentence ranking</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Мы благодарим «Яндекс.Маркет» и «YM Сканнер» за материалы для исследования</funding-statement><funding-statement xml:lang="en">We are grateful to Yandex.Market and YM Scanner for the research materials</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Борисова Е. Г. Маркетинговая лингвистика: направления и перспективы // Верхневолжский филологический вестник. 2016. № 4. С. 140–143.</mixed-citation><mixed-citation xml:lang="en">Akhtar, N. et al. Aspect based sentiment oriented summarization of hotel reviews. Procedia computer science, 2017, vol. 115, pp. 563–571.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">РД 50-165-79 Товары народного потребления. Выбор номенклатуры потребительских свойств и показателей качества. Основные положения [Электронный ресурс]. URL: https://files.stroyinf.ru/Index2/1/4293762/4293762287.htm (дата обращения: 28.05.2022).</mixed-citation><mixed-citation xml:lang="en">Bojanowski, P. et al. Enriching word vectors with subword information. Transactions of the association for computational linguistics, 2017, vol. 5, pp. 135–146.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Рубашкин В. Ш. Онтологическая семантика. Знания. Онтологии. Онтологически ориентированные методы информационного анализа текстов. М.: Физматлит, 2012. 348 с.</mixed-citation><mixed-citation xml:lang="en">Borisova, E. G. Marketing linguistics: prospects and trends. Verhnevolzhski philological bulletin, 2016, no. 4, pp. 140–143.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Akhtar N. et al. Aspect based sentiment oriented summarization of hotel reviews // Procedia computer science. 2017. Т. 115. Pp. 563–571.</mixed-citation><mixed-citation xml:lang="en">Brokos, G. I., Malakasiotis, P., Androutsopoulos, I. Using centroids of word embeddings and word mover’s distance for biomedical document retrieval in question answering. Proceedings of the 15th Workshop on Biomedical Natural Language Processing, 2016, pp. 114–118.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Bojanowski P. et al. Enriching word vectors with subword information // Transactions of the association for computational linguistics. 2017. Vol. 5. Pp. 135–146.</mixed-citation><mixed-citation xml:lang="en">Condori, R. E. L., Pardo, T. A. S. Opinion summarization methods: Comparing and extending extractive and abstractive approaches. Expert Systems with Applications, 2017, vol. 78, pp. 124– 134.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Brokos G. I., Malakasiotis P., Androutsopoulos I. Using centroids of word embeddings and word mover’s distance for biomedical document retrieval in question answering // Proceedings of the 15th Workshop on Biomedical Natural Language Processing, 2016. Pp. 114–118.</mixed-citation><mixed-citation xml:lang="en">d’Sa, A. G. et al. Label propagation-based semi-supervised learning for hate speech classification. Insights from Negative Results Workshop, EMNLP, 2020.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Condori R. E. L., Pardo T. A. S. Opinion summarization methods: Comparing and extending extractive and abstractive approaches // Expert Systems with Applications. 2017. Vol. 78. Pp. 124–134.</mixed-citation><mixed-citation xml:lang="en">Ellson, J. et al. Graphviz and dynagraph—static and dynamic graph drawing tools. Graph drawing software. Springer, Berlin, Heidelberg, 2004, pp. 127–148.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">d’Sa A. G. et al. Label propagation-based semi-supervised learning for hate speech classification // Insights from Negative Results Workshop, EMNLP, 2020.</mixed-citation><mixed-citation xml:lang="en">Fishbein, M. An investigation of the relationships between beliefs about an object and the attitude toward that object. Human relations, 1963, vol. 16, no. 3, pp. 233–239.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Ellson J. et al. Graphviz and dynagraph—static and dynamic graph drawing tools // Graph drawing software. Springer, Berlin, Heidelberg, 2004. Pp. 127–148.</mixed-citation><mixed-citation xml:lang="en">Howard, J. A. Consumer behavior: Application of theory. McGraw-Hill Companies. 1977.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Fishbein M. An investigation of the relationships between beliefs about an object and the attitude toward that object // Human relations. 1963. Vol. 16, № 3. Pp. 233–239.</mixed-citation><mixed-citation xml:lang="en">Johnson, E. J., Tversky, A. Representations of Perceptions of Risk. Journal of Experimental Psychology: General, 1984, pp. 55–70.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Howard J. A. Consumer behavior: Application of theory. McGraw-Hill Companies. 1977.</mixed-citation><mixed-citation xml:lang="en">Hu, M., Liu, B. Mining and summarizing customer reviews. Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, 2004, pp. 168–177.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Johnson E. J., Tversky A. Representations of Perceptions of Risk // Journal of Experimental Psychology: General, 1984. Pp. 55–70.</mixed-citation><mixed-citation xml:lang="en">Joulin, A., Grave, E., Bojanowski, P., Mikolov, T. Bag of Tricks for Efficient Text Classification. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017, pp. 427–431.</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Hu M., Liu B. Mining and summarizing customer reviews // Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, 2004. Pp. 168–177.</mixed-citation><mixed-citation xml:lang="en">Kim, S. et al. A hierarchical aspect-sentiment model for online reviews. Proceedings of the AAAI Conference on Artificial Intelligence, 2013, vol. 27, pp. 526–533.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Kim S. et al. A hierarchical aspect-sentiment model for online reviews // Proceedings of the AAAI Conference on Artificial Intelligence. 2013. Vol. 27. Pp. 526–533.</mixed-citation><mixed-citation xml:lang="en">Kotler, F. Marketing Management: Analysis, Planning, and Control. Prentice-Hall, 1967, 628 p.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Joulin A., Grave E., Bojanowski P., Mikolov T. Bag of Tricks for Efficient Text Classification // Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 2017. Pp. 427–431.</mixed-citation><mixed-citation xml:lang="en">Lancaster, K. J. A new approach to consumer theory. Journal of political economy, 1966, vol. 74, no. 2, pp. 132–157.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Kotler F. Marketing Management: Analysis, Planning, and Control. Prentice-Hall. 1967. 628 p.</mixed-citation><mixed-citation xml:lang="en">Mihalcea, R., Tarau, P. Textrank: Bringing order into text. Proceedings of the 2004 conference on empirical methods in natural language processing. 2004, pp. 404–411.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Lancaster K. J. A new approach to consumer theory // Journal of political economy. 1966. Vol. 74, № 2. Pp. 132–157</mixed-citation><mixed-citation xml:lang="en">Mithun, S., Kosseim, L. Summarizing blog entries versus news texts. Proceedings of the Workshop on Events in Emerging Text Types. 2009, pp. 1–8</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Mihalcea R., Tarau P. Textrank: Bringing order into text // Proceedings of the 2004 conference on empirical methods in natural language processing. 2004. Pp. 404–411.</mixed-citation><mixed-citation xml:lang="en">Mukherjee, A., Liu, B. Aspect extraction through semi-supervised modeling. Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2012, pp. 339–348.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Mithun S., Kosseim L. Summarizing blog entries versus news texts // Proceedings of the Workshop on Events in Emerging Text Types. 2009. Pp. 1–8</mixed-citation><mixed-citation xml:lang="en">RD 50-165-79 Consumer goods. Selection of the nomenclature of consumer properties and quality indicators. The main features [Online]. URL: https://files.stroyinf.ru/Index2/1/4293762/4293762287.htm (accesed on: 28.05.2022) (in Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Mukherjee A., Liu B. Aspect extraction through semi-supervised modeling // Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2012. Pp. 339–348.</mixed-citation><mixed-citation xml:lang="en">Rosenberg, M. J. Cognitive structure and attitudinal affect. The Journal of abnormal and social psychology, 1956, vol. 53, no. 3, p. 367.</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Rosenberg M. J. Cognitive structure and attitudinal affect // The Journal of abnormal and social psychology. 1956. Vol. 53, № 3. P. 367.</mixed-citation><mixed-citation xml:lang="en">Rubashkin, V. Ontological semantics. Knowledge. Ontologies. Ontology-based approach to information analysis of text. Moscow, Fizmatlit, 2012, 348 p. (in Russ.)</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Thaler R. Toward a positive theory of consumer choice // Journal of economic behavior &amp; organization. 1980. Vol. 1, № 1. Pp. 39–60.</mixed-citation><mixed-citation xml:lang="en">Thaler, R. Toward a positive theory of consumer choice. Journal of economic behavior &amp; organization, 1980, vol. 1, no. 1, pp. 39–60.</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Tversky A., Kahneman D. Judgment under uncertainty: Heuristics and biases // Science. 1974. Vol. 185, № 4157. Pp. 1124–1131.</mixed-citation><mixed-citation xml:lang="en">Tversky, A., Kahneman, D. Judgment under uncertainty: Heuristics and biases. Science, 1974, vol. 185, no. 4157, pp. 1124–1131.</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Zhai Z. et al. Clustering product features for opinion mining // Proceedings of the fourth ACM international conference on Web search and data mining. 2011. Pp. 347–354</mixed-citation><mixed-citation xml:lang="en">Zhai, Z. et al. Clustering product features for opinion mining. Proceedings of the fourth ACM international conference on Web search and data mining, 2011, pp. 347–354</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Yu J. et al. Domain-assisted product aspect hierarchy generation: towards hierarchical organization of unstructured consumer reviews // Proceedings of the 2011 conference on empirical methods in natural language processing. 2011. Pp. 140–150.</mixed-citation><mixed-citation xml:lang="en">Yu, J. et al. Domain-assisted product aspect hierarchy generation: towards hierarchical organization of unstructured consumer reviews. Proceedings of the 2011 conference on empirical methods in natural language processing, 2011, pp. 140–150.</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>
