Analysis of the mutual dynamics of stock quotes and the sentiment of textual mentions in the media of the company "OZON Holdings PLC" using correlation and sentiment analysis.

Cover Page

Cite item

Full Text

Abstract

The subject of this scientific research is the study of the relationship between the dynamics of the stock prices of "Ozon Holdings PLC" and the sentiment of its mentions in the media. In the context of the rapid growth of the information flow and its impact on financial markets, the analysis of how the news background influences investor behavior and, consequently, the stock prices of companies, becomes particularly relevant. "Ozon Holdings PLC," as one of the leading players in e-commerce in Russia, was chosen as the research object due to the high frequency of its media mentions and the noticeable volatility of its shares. The study aims to identify patterns demonstrating whether the positive or negative sentiment of news publications influences the movement of the company's stock prices. Such understanding can be useful for investors, analysts, and financial specialists seeking to consider not only quantitative but also qualitative (textual) data in forecasting market dynamics. For the analysis, news articles from 2021 to 2024 were collected using Google Chrome tools. The sentiment of the texts was assessed using the DeepPavlov/rubert-base-cased-conversational model. A correlation analysis was then conducted to explore the relationship between the dynamics of Ozon's stock prices and the sentiment of the news background. The scientific novelty of this research lies in the application of sentiment analysis methods based on modern language models to the task of studying the influence of the media landscape on the stock market, which is relevant in the context of the growing importance of information flows for investors and analysts. For the first time, a systematic evaluation of the relationship between the sentiment of news mentions about "Ozon Holdings PLC" and changes in its stock prices over a three-year period was conducted. The results of the correlation analysis demonstrated a statistically significant connection between the positive or negative sentiment of news and the subsequent movement of stock prices. The conclusions of the research can be used to construct predictive models for assessing risk and stock behavior based on the informational background, as well as as a tool for making investment decisions. The data presented supports the hypothesis regarding the influence of the media environment on the financial performance of companies, especially in conditions of instability or significant information triggers.

References

  1. Михненко П. А. Трансформация деловой лексики годовых отчетов крупнейших российских компаний: data mining // Управленец. 2022. Т. 13, № 5. С. 68-83. doi: 10.29141/2218-5003-2022-13-5-2. EDN: DLNXWM.
  2. Богданов А. Л., Дуля И. С. Сентимент-анализ коротких русскоязычных текстов в социальных медиа // Вестник Томского государственного университета. Экономика. 2019. № 47. С. 148-163. doi: 10.17223/19988648/47/17. EDN: QFXMQA.
  3. Жукова Н. Ю., Меликова А. Э. Социальная ответственность бизнеса: усиление стоимости бренда и влияние на финансовые показатели компании // Финансы: теория и практика. 2021. Т. 25, № 1. С. 136-149. doi: 10.26794/2587-5671-2021-25-1-84-102. EDN: TKZNFS.
  4. Лихонос В. О. Влияние имиджа организации на результаты ее деятельности // Теория и практика современной науки. 2019. № 6 (48). С. 103-106.
  5. Садковкин А. А., Зорина М. В. Влияние публикации в СМИ на финансовые показатели компании: анализ взаимосвязи между пресс-релизами и стоимостью акций // Экономика и бизнес: теория и практика. 2023. № 9 (103). С. 141-144.
  6. Федорова Е. А., Лапшина Н. В., Лазарев М. П., Бородин А. И. Влияние информации в пресс-релизах на финансовые показатели российских компаний // Экономическая политика. 2021. Т. 16, № 3. С. 86-109.
  7. Романов С. А. Влияние публикаций в СМИ на финансовые результаты деятельности российских банков (на примере ПАО "Сбербанк") // Известия Санкт-Петербургского государственного экономического университета. 2024. № 2 (146). С. 87-93.
  8. Haas C., Budin C., d'Arcy A. How to select oil price prediction models-The effect of statistical and financial performance metrics and sentiment scores // Energy Economics. 2024. Vol. 133. P. 107466. DOI: https://doi.org/10.1016/j.eneco.2024.107466. EDN: VTGBPM.
  9. Hogenboom A., Brojba-Micu A., Frasincar F. The impact of word sense disambiguation on stock price prediction // Expert Systems with Applications. 2021. Vol. 184. P. 115568. DOI: https://doi.org/10.1016/j.eswa.2021.115568. EDN: CYBVUZ.
  10. Loutfi A. Renewable energy stock prices forecast using environmental television newscasts investors' sentiment // Renewable Energy. 2024. Vol. 230. P. 120873. DOI: https://doi.org/10.1016/j.renene.2024.120873. EDN: ZECGGZ.
  11. Kang W., Yuan X., Zhang X., Chen Y., Li J. ChatGPT-based sentiment analysis and risk prediction in the Bitcoin market // Procedia Computer Science. 2024. Vol. 242. Pp. 211-218. DOI: https://doi.org/10.1016/j.procs.2024.08.258. EDN: MXPTBR.
  12. Selimovic M., Almisreb A. A., Amanzholova S. The role of sentiment analysis in brand management and marketing: A comparative study // Procedia Computer Science. 2024. Vol. 251. Pp. 579-584. DOI: https://doi.org/10.1016/j.procs.2024.11.152. EDN: XRAKIT.
  13. Akdogan Y. E., Anbar A. More than just sentiment: Using social, cognitive, and behavioral information of social media to predict stock markets with artificial intelligence and big data // Borsa Istanbul Review. 2024. Vol. 24, No. 6. Pp. 1788-1801. DOI: https://doi.org/10.1016/j.bir.2024.12.003. EDN: OEROOU.
  14. Varghese R., Mohan B. Study on the sentimental influence on Indian stock price // Heliyon. 2023. Vol. 9. P. e22788. DOI: https://doi.org/10.1016/j.heliyon.2023.e22788. EDN: RGZKHP.
  15. Jena P., Majhi R. Are Twitter Sentiments During COVID-19 Pandemic a Critical Determinant to Predict Stock Market Movements? A Machine Learning Approach // Scientific African. 2022. Vol. 17. P. e01480. DOI: https://doi.org/10.1016/j.sciaf.2022.e01480. EDN: SMXBJQ.
  16. Sun Y., Liu X., Chen G., Hao Y., Zhang J. How Mood Affects the Stock Market: Empirical Evidence from Microblogs // Information & Management. 2020. Vol. 57, No. 7. P. 103181. DOI: https://doi.org/10.1016/j.im.2019.103181. EDN: BGAFZI.
  17. Abdullah M., Sulong Z., Chowdhury M. A. Explainable deep learning model for stock price forecasting using textual analysis // Expert Systems with Applications. 2024. Vol. 249. P. 123740. DOI: https://doi.org/10.1016/j.eswa.2024.123740. EDN: KOMPFC.
  18. Maqbool J., Masood A., Bashir S., Alhussain T., Aldosary S., Khadim H. Stock prediction by integrating sentiment scores of financial news and MLP-regressor: A machine learning approach // Procedia Computer Science. 2023. Vol. 218. Pp. 1067-1078. DOI: https://doi.org/10.1016/j.procs.2023.01.086. EDN: QJTVAN.
  19. Daudert T. Exploiting textual and relationship information for fine-grained financial sentiment analysis // Knowledge-Based Systems. 2021. Vol. 230. P. 107389. DOI: https://doi.org/10.1016/j.knosys.2021.107389. EDN: LRUGQA.
  20. Ferraro A., Sperlì G. How does user-generated content on Social Media affect stock predictions? A case study on GameStop // Online Social Networks and Media. 2024. Vol. 43. P. 100293. DOI: https://doi.org/10.1016/j.osnem.2024.100293. EDN: LJCYGW.
  21. Nyakurukwa K., Seetharam Y. The evolution of studies on social media sentiment in the stock market: Insights from bibliometric analysis // Scientific African. 2023. Vol. 20. P. e01596. DOI: https://doi.org/10.1016/j.sciaf.2023.e01596. EDN: MHJTIW.
  22. Lin Z. Impact of investor sentiment on firm innovation: Evidence from textual analysis // Borsa Istanbul Review. 2023. Vol. 23, No. 5. Pp. 1141-1151. DOI: https://doi.org/10.1016/j.bir.2023.04.006. EDN: DVMZKD.
  23. Lin W., Liao L. C. Lexicon-based prompt for financial dimensional sentiment analysis // Expert Systems with Applications. 2024. Vol. 244. P. 122936. DOI: https://doi.org/10.1016/j.eswa.2024.122936. EDN: LRMSKX.
  24. George M. Improving sentiment analysis of financial news headlines using hybrid Word2Vec-TFIDF feature extraction technique // Procedia Computer Science. 2024. Vol. 244. Pp. 1-8. DOI: https://doi.org/10.1016/j.procs.2024.08.233. EDN: NYPKCS.
  25. Das N., Chakrabarty A., Dutta R., Bhattacharya S., Dutta P. Integrating sentiment analysis with graph neural networks for enhanced stock prediction: A comprehensive survey // Decision Analytics Journal. 2024. Vol. 11. P. 100417. DOI: https://doi.org/10.1016/j.dajour.2024.100417. EDN: XOIRNO.
  26. Kitiwong W., Ekasingh E., Sarapaivanich N. Analysis of non-English key audit matters: Do key audit matters influence investor sentiment? // Journal of International Accounting, Auditing and Taxation. 2024. Vol. 55. P. 100670. DOI: https://doi.org/10.1016/j.intaccaudtax.2024.100670.
  27. Fernandez R., Guizar B. P., Rho C. A sentiment-based risk indicator for the Mexican financial sector // Latin American Journal of Central Banking. 2021. Vol. 2, No. 3. P. 100036. DOI: https://doi.org/10.1016/j.latcb.2021.100036. EDN: MTJFWC.
  28. Ge Y., Liu C., Xiong H., Chen J. Beyond negative and positive: Exploring the effects of emotions in social media during the stock market crash // Information Processing & Management. 2020. Vol. 57, No. 4. P. 102218. DOI: https://doi.org/10.1016/j.ipm.2020.102218. EDN: GKIRLB.
  29. Gui J., Luo Z., Wu H., Wang T., Xu B. Measuring investor sentiment of China's growth enterprises market with ERNIE // Procedia Computer Science. 2022. Vol. 202. Pp. 1-8. DOI: https://doi.org/10.1016/j.procs.2022.04.001. EDN: PORMGG.
  30. Ren Y., Liao F., Gong Y. Impact of news on the trend of stock price change: An analysis based on the deep bidirectional LSTM model // Procedia Computer Science. 2020. Vol. 174. Pp. 128-140. DOI: https://doi.org/10.1016/j.procs.2020.06.066. EDN: KBMRHM.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).