Computational nanotechnologyComputational nanotechnologyComputational nanotechnologyComputational nanotechnologyComputational nanotechnologyComputational nanotechnology2313-223X2587-9693YUR-VAK52984910.33693/2313-223X-2022-9-2-35-44ArticlesСтатьиResearch ArticleElements of artificial intelligence in solving problems of text analysisЭлементы искусственного интеллекта в решении задач анализа текстовKaterminaTatyana S.КатерминаТатьяна Сергеевна

Cand. Sci. (Eng.); associate professor at the Department of Informatics and Methods of Teaching Informatics

кандидат технических наук; доцент кафедры информатики и методики преподавания информатики

nggu-lib@mail.ruTagirovKadir M.ТагировКадир Межвединович

master; teacher

магистр; преподаватель

kadir.tagirov1997@gmail.comTagirovTagir M.ТагировТагир Межвединович

master; teacher

магистр; преподаватель

agirov97bocman@gmail.comNizhnevartovsk State UniversityНижневартовский государственный университет»1506202292VOL 9, NO2 (2022)ТОМ 9, №2 (2022)354405072023Copyright ©; 2022, Yur-VAKCopyright ©; 2022, Юр-ВАК2022Yur-VAKЮр-ВАКhttps://journals.eco-vector.com/2313-223X/about/editorialPolicieshttps://journals.eco-vector.com/2313-223X/article/view/529849

Due to the ever-increasing volume of textual information on the Internet and the need to navigate it, the automation of the text analysis process has become urgent. The analysis of the subject area has shown a great demand for the identification of textual information coloring and the application of works on this problem in practice. This paper deals with the development of a neural network model for analyzing commentary tone. Recurrent neural network models with long short-term memory modules (LSTM) are used for the purpose. We have developed an information system that determines the tone of comments on posts in the communities of the social network “VKontakte”. As a result of training of the artificial neural network, the model showed good accuracy in determining the tone of the text. The information system was implemented in the marketing department of the Nizhnevartovsk Construction College Budget Institution.

В связи с постоянно растущим объемом текстовой информации в интернете и потребностью в ней ориентироваться, становиться актуальным автоматизация процесса анализа текста. Анализ предметной области показал большой интерес к определению эмоциональной окраски текстовой информации и применению трудов по этой проблеме в различных областях экономики. В работе рассматривается разработка модели нейронной сети для анализа тональности сообщений в социальных сетях сети Интернет. Для решения поставленной цели используются модели рекуррентных нейронных сетей с модулями долгой краткосрочной памятью (LSTM). Разработана информационная система, которая определяет тональность комментариев к постам в сообществах социальной сети «ВКонтакте». В результате обучения искусственной нейронной сети, модель показала хорошую точность определения тональности текста. Информационная система внедрена в отдел маркетинга Бюджетного учреждения Нижневартовского строительного колледжа.

sentiment analysisartificial neural networksmachine learningrecurrent neural networkslong short-term memorynatural language processingанализ тональности текстаискусственные нейронные сетимашинное обучениерекуррентные нейронные сетидлинная цепь элементов краткосрочной памятиобработка естественного языкаAbbasi A., Javed A.R., Iqbal F. et al. Authorship identification using ensemble learning. Scientific Reports. 2022. No. 12 (1). DOI: 10.1038/s41598-022-13690-4.Alibasic A., Upadhyay H., Simsekler M.C.E. et al. Evaluation of the trends in jobs and skill-sets using data analytics: A case study. Journal of Big Data. 2022. No. 9 (1). DOI: 10.1186/s40537-022-00576-5.Lee C.K.M., Kam K.H. Ng, Chun-Hsien Chen et al. Tiffany Tsoi, American sign language recognition and training method with recurrent neural network. Expert Systems with Applications. 2021. Vol. 167.Khurshid S., Reeder C., Harrington L.X. et al. Cohort design and natural language processing to reduce bias in electronic health records research. Npj Digital Medicine. 2022. Vol. 5. No. 47. URL: https://doi.org/10.1038/s41746-022-00590-0Ledro C., Nosella A., Vinelli A. Artificial intelligence in customer relationship management: Literature review and future research directions. Journal of Business and Industrial Marketing. 2022. No. 37 (13). Pp. 48-63. DOI: 10.1108/JBIM-07-2021-0332.Li S., Wang G., Luo Y. Tone of language, financial disclosure, and earnings management: A textual analysis of form 20-F. Financial Innovation. 2022. No. 8 (1). DOI: 10.1186/s40854-022-00346-5.Luo Z., Zhu M. Recurrent neural networks with mixed hierarchical structures for natural language processing.International Joint Conference on Neural Networks (IJCNN). 2021. Pp. 1-8. DOI: 10.1109/IJCNN52387.2021.9533347.Mohd Usama, Belal Ahmad, Enmin Song et al. Attention-based sentiment analysis using convolutional and recurrent neural network. Future Generation Computer Systems. 2020. Pp. 571-578.Nijhawan T., Attigeri G., Ananthakrishna T. Stress detection using natural language processing and machine learning over social interactions. Journal of Big Data. 2022. No. 9 (1). DOI: 10.1186/s40537-022-00575-6.Orea-Giner A., Fuentes-Moraleda L., Villacé-Molinero T. et al. Does the implementation of robots in hotels influence the overall tripadvisor rating? A text mining analysis from the Industry 5.0 approach. Tourism Management. 2022. No. 93. DOI: 10.1016/j.tourman.2022.104586.Riezler S., Hagmann M. Validity, reliability, and significance: Empirical methods for NLP and data science. Synthesis Lectures on Human Language Technologies. 2022. No. 14 (6). Pp. 1-147. DOI: 10.2200/S01137ED1V01Y202110HLT055.Sherstinsky A. Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network. Physica D: Nonlinear Phenomena. 2020. Vol. 404.Turner R.J., Coenen F., Roelofs F. et al. Information extraction from free text for aiding transdiagnostic psychiatry: Constructing NLP pipelines tailored to clinicians’ needs. BMC Psychiatry. 2022. No. 22 (1). DOI: 10.1186/s12888-022-04058-z.Dankers V., Langedijk A., McCurdy K. et al. Generalising to German plural noun classes, from the perspective of a recurrent neural network. Proceedings of the 25th Conference on Computational Natural Language Learning. 2021. Pp. 94-108.Zhang T., Schoene A.M., Ji S., Ananiadou S. Natural language processing applied to mental illness detection: A narrative review. Npj Digital Medicine. 2022. No. 5 (1). DOI: 10.1038/s41746-022-00589-7.