<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article 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" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="research-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Economics and Mathematical Methods</journal-id><journal-title-group><journal-title xml:lang="en">Economics and Mathematical Methods</journal-title><trans-title-group xml:lang="ru"><trans-title>Экономика и математические методы</trans-title></trans-title-group></journal-title-group><issn publication-format="print">0424-7388</issn><issn publication-format="electronic">3034-6177</issn><publisher><publisher-name xml:lang="en">The Russian Academy of Sciences</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">682164</article-id><article-id pub-id-type="doi">10.31857/S0424738825010095</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>Mathematical analysis of economic models</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>Математический анализ экономических моделей</subject></subj-group><subj-group subj-group-type="article-type"><subject>Research Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">Forecasting Russian stock returns based on investor sentiment analysis in social networks</article-title><trans-title-group xml:lang="ru"><trans-title>Прогнозирование доходности российских акций на основе анализа сентимента инвесторов в социальных сетях</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Khaziev</surname><given-names>G. A.</given-names></name><name xml:lang="ru"><surname>Хазиев</surname><given-names>Г. А.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><email>gakhaziev@hse.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Sokolova</surname><given-names>T. V.</given-names></name><name xml:lang="ru"><surname>Соколова</surname><given-names>Т. В.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><email>tv.sokolova@hse.ru</email><xref ref-type="aff" rid="aff2"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">National Research University Higher School of Economics (HSE University)</institution></aff><aff><institution xml:lang="ru">НИУ «Высшая школа экономики»</institution></aff></aff-alternatives><aff-alternatives id="aff2"><aff><institution xml:lang="en">National Research University Higher School of Economics, (HSE University)</institution></aff><aff><institution xml:lang="ru">НИУ «Высшая школа экономики»</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2025-04-16" publication-format="electronic"><day>16</day><month>04</month><year>2025</year></pub-date><volume>61</volume><issue>1</issue><fpage>95</fpage><lpage>108</lpage><history><date date-type="received" iso-8601-date="2025-06-03"><day>03</day><month>06</month><year>2025</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2025, Russian Academy of Sciences</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2025, Российская академия наук</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="en">Russian Academy of Sciences</copyright-holder><copyright-holder xml:lang="ru">Российская академия наук</copyright-holder></permissions><self-uri xlink:href="https://journals.eco-vector.com/0424-7388/article/view/682164">https://journals.eco-vector.com/0424-7388/article/view/682164</self-uri><abstract xml:lang="en"><p>The study explores the sentiment of Russian private investors in social networks and its impact on the dynamics of the stock return of 78 companies on the Russian stock market (MOEX) in the period from 2018 to 2022. To take into account sentiment when forecasting returns, the authors RSMI index (Russian social media index) is used, which is based on a unique sample of messages from the most popular social networks among Russian investors — “Telegram” and “Tinkoff Pulse”. The RSMI index includes quantitative (the number of publications in relation to each company) and qualitative (investor reactions) characteristics, allowing to determine the real impact of a particular publication on investors. Using the RSMI index, several models for predicting stock prices of Russian companies were used: lasso regression, random forest, gradient boosting, extreme gradient boosting, ensemble learning and long short-term memory. It is demonstrated that for a wide sample of stocks, indicators of technical and fundamental analysis play a large role in building forecasts of changes in stock returns based on hourly data. Although the addition of the sentiment index improves the results of predicting returns for a wide sample of stocks, it does not significantly improve the predictive ability of the models and shows mixed results. The best results of adding the sentiment index to forecast models are shown for the top 15 most discussed Russian companies. For individual models, we achieved an average error reduction of 4.9%, and at the level of specific companies, the MAE error rate was reduced by more than 10% and MSE by 20%. It has been proven that the returns of low-liquidity stocks of the second and third tiers of the Russian stock market are not significantly influenced by the sentiment of private investors on hourly data, and the addition of the sentiment index does not improve the results of forecast models.</p></abstract><trans-abstract xml:lang="ru"><p>В работе исследуется сентимент российских частных инвесторов в социальных сетях и его влияние на динамику доходности акций 78 компаний российского рынка в 2018–2022 г. Для учета сентимента при прогнозировании цен используется авторский индекс RSMI (Russian social media index), который строится на уникальной выборке сообщений из наиболее популярных у российских инвесторов социальных сетей — «Телеграм» и «Тинькофф Пульс». Индекс RSMI включает количественные (число публикаций в отношении каждой компании) и качественные (реакции инвесторов) характеристики, позволяющие определить реальное влияние той или иной публикации на инвесторов. С использованием индекса RSMI построены модели прогнозирования цен акций российских компаний методами регрессии «лассо» (lasso), «случайного леса», градиентного бустинга, экстремального градиентного бустинга, ансамблевого обучения и рекуррентной нейронной сети (LSTM). Показано, что для акций широкой выборки индикаторы технического анализа и рыночные мультипликаторы играют большую роль в построении прогнозов изменения доходности акций на часовых данных. Хотя добавление индекса сентимента и позволяет улучшить результаты прогнозирования доходности для акций широкой выборки, это не дает значительного улучшения предсказательной способности моделей и показывает разнонаправленные результаты. Наилучшие результаты добавление индекса сентимента в прогнозные модели показывает для топ-15 наиболее обсуждаемых российских компаний. Для отдельных моделей удалось добиться среднего снижения ошибок на 4,9%, а для отдельных компаний более чем на 10% уменьшить показатель ошибки MAE и на 20% MSE. Доказано, что на динамику доходности акций второго и третьего эшелона российского фондового рынка сентимент частных инвесторов на часовых данных не оказывает существенного влияния, а добавление индекса сентимента не позволяет улучшить результаты прогнозных моделей.</p></trans-abstract><kwd-group xml:lang="en"><kwd>stocks</kwd><kwd>stock market</kwd><kwd>machine learning</kwd><kwd>investor sentiment</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>акции</kwd><kwd>фондовый рынок</kwd><kwd>машинное обучение</kwd><kwd>сентимент инвесторов</kwd></kwd-group><funding-group><funding-statement xml:lang="en">Russian Science Foundation №22-18-002760</funding-statement><funding-statement xml:lang="ru">Российский научный фонд №22-18-002760</funding-statement></funding-group></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><mixed-citation>Теплова Т. В., Соколова Т. В., Томтосов А. Ф., Бучко Д. В., Никулин Д. Д. (2022). Сентимент частных инвесторов в объяснении различий в биржевых характеристиках акций российского рынка // Журнал Новой экономической ассоциации. № 1 (53). C. 53–84. [Teplova T. V., Sokolova T. V., Tomtosov A. F., Buchko D. V., Nikulin D. D. (2022). The sentiment of private investors in explaining the differences in the trade characteristics of the Russian market stocks. Journal of the New Economic Association, 1 (53), 53–84 (in Russian).]</mixed-citation></ref><ref id="B2"><label>2.</label><mixed-citation>Agrawal T. J., Sehgal S., Vasishth V. (2020). Firm attributes, corporate fundamentals and investment strategies: An empirical study for Indian stock market. Management and Labour Studies, 45 (3), 366–387. DOI: 10.1177/0258042X20927995</mixed-citation></ref><ref id="B3"><label>3.</label><mixed-citation>Ahmed D., Neema R., Visqanadha N. (2022). Analysis and prediction of healthcare sector stock price using machine learning techniques: Healthcare stock analysis. International Journal of Information System Modeling and Design, 13, 9, 1–15. DOI: 10.4018/IJISMD.303131</mixed-citation></ref><ref id="B4"><label>4.</label><mixed-citation>Aslim M. F., Firmansyah G., Tjahjono B., Akbar H., Widodo A. M. (2024). Utilization of LSTM (Long Short Term Memory) based sentiment analysis for stock price prediction. Asian Journal of Social &amp; Humanities, 1, 12, 1241– 1255. DOI: 10.59888/ajosh.v1i12.141</mixed-citation></ref><ref id="B5"><label>5.</label><mixed-citation>Audrino F., Sigrist F., Ballinari D. (2020). The impact of sentiment and attention measures on stock market volatility. International Journal of Forecasting, 36, 2, 334–357.</mixed-citation></ref><ref id="B6"><label>6.</label><mixed-citation>Baker M., Wurgler J. (2007). Investor sentiment in the stock market. Journal of Economic Perspectives, 21, 2, 129–152.</mixed-citation></ref><ref id="B7"><label>7.</label><mixed-citation>Basu S. (1983). The relationship between earnings yield, market value and return for NYSE Common Stocks. Journal of Financial Economics, 12, 129–156. DOI: 10.1016/0304-405X(83)90031-4</mixed-citation></ref><ref id="B8"><label>8.</label><mixed-citation>Bui D. G., Kong D.-R., Lin C.-Y., Lin T.-C. (2023). Momentum in machine learning: Evidence from the Taiwan stock market. Pacific-Basin Finance Journal, 82. Article 102178. DOI: 10.1016/j.pacfin.2023.102178</mixed-citation></ref><ref id="B9"><label>9.</label><mixed-citation>Cai Y., Tang Z., Chen Y. (2024). Can real-time investor sentiment help predict the high frequency stock returns? Evidence from a mixed-frequency-rolling decomposition forecasting method. North American Journal of Economics &amp; Finance, 72. Article 102147. DOI: 10.1016/j.najef.2024.102147</mixed-citation></ref><ref id="B10"><label>10.</label><mixed-citation>Chen S., Ge L. (2019). Exploring the attention mechanism in LSTM-based Hong Kong stock price movement prediction. Quantitative Finance, 19, 9, 1507–1515.</mixed-citation></ref><ref id="B11"><label>11.</label><mixed-citation>Chong E., Han C., Park F. C. (2017). Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies. Expert Systems with Applications, 83, 187–205.</mixed-citation></ref><ref id="B12"><label>12.</label><mixed-citation>Fama E. F. (1965). The behavior of stock-market prices. Journal of Business, 38, 34, Article 105.</mixed-citation></ref><ref id="B13"><label>13.</label><mixed-citation>Gao B., Xie J. (2020). Forecasting excess returns and abnormal trading, using investor sentiment: Evidence from Chinese stock index futures market. Emerging Markets Finance and Trade, 56, 3, 593–612.</mixed-citation></ref><ref id="B14"><label>14.</label><mixed-citation>Gao Y., Zhao C., Sun B., Zhao W. (2022). Effects of investor sentiment on stock volatility: New evidences from multi-source data in China’s green stock markets. Financial Innovation, 8, Article 77.</mixed-citation></ref><ref id="B15"><label>15.</label><mixed-citation>Gu C., Kurov A. (2020). Informational role of social media: Evidence from Twitter sentiment. Journal of Banking &amp; Finance, 121, Article 105969.</mixed-citation></ref><ref id="B16"><label>16.</label><mixed-citation>Gupta R., Nel J., Pierdzioch C. (2023). Investor confidence and forecastability of US stock market realized volatility: Evidence from machine learning. Journal of Behavioral Finance, 24, 1, 111–122.</mixed-citation></ref><ref id="B17"><label>17.</label><mixed-citation>Li T., Chen H., Liu W., Yu G., Yu Y. (2023). Understanding the role of social media sentiment in identifying irrational herding behavior in the stock market. International Review of Economics &amp; Finance, 87, 163–179. DOI: 10.1016/ j.iref.2023.04.016</mixed-citation></ref><ref id="B18"><label>18.</label><mixed-citation>Li Y., Bu H., Li J., Wu J. (2020). The role of text-extracted investor sentiment in Chinese stock price prediction with the enhancement of deep learning. International Journal of Forecasting, 36 (4), 1541–1562.</mixed-citation></ref><ref id="B19"><label>19.</label><mixed-citation>Liang C., Tang L., Li Y., Wei Y. (2020). Which sentiment index is more informative to forecast stock market volatility? Evidence from China. International Review of Financial Analysis, 71, Article 101552.</mixed-citation></ref><ref id="B20"><label>20.</label><mixed-citation>Lin P., Ma S., Fildes R. (2024). The extra value of online investor sentiment measures on forecasting stock return volatility: A large-scale longitudinal evaluation based on Chinese stock market. Expert Systems with Applications, 238, Article 121927. DOI: 10.1016/j.eswa.2023.121927</mixed-citation></ref><ref id="B21"><label>21.</label><mixed-citation>Liu J.-X., Leu J.-S., Holst S. (2023). Stock price movement prediction based on stocktwits investor sentiment using FinBERT and ensemble SVM. PeerJ Computer Science, 9, Article e1403. DOI: 10.7717/peerj-cs.1403</mixed-citation></ref><ref id="B22"><label>22.</label><mixed-citation>Liu Q., Lee W.-S., Huang M., Wu Q. (2023). Synergy between stock prices and investor sentiment in social media. Borsa Istanbul Review, 23, 1, 76–92. DOI: 10.1016/j.bir.2022.09.006</mixed-citation></ref><ref id="B23"><label>23.</label><mixed-citation>Mili M., Sahut J.-M., Teulon F., Hikkerova L. (2024). A multidimensional Bayesian model to test the impact of investor sentiment on equity premium. Annals of Operations Research, 334, 1–3, 919–39. DOI: 10.1007/s10479-023-05165-0</mixed-citation></ref><ref id="B24"><label>24.</label><mixed-citation>Navratil R., Taylor S., Vecer J. (2021). On equity market inefficiency during the COVID-19 pandemic. International Review of Financial Analysis, 77, Article 101820. DOI: 10.1016/j.irfa.2021.101820</mixed-citation></ref><ref id="B25"><label>25.</label><mixed-citation>Neely C., Rapach D. E., Tu J., Zhou G. (2014). Forecasting the equity risk premium: The role of technical indicators. Management Science, 60, 7, 1772–1791. DOI: 10.1287/mnsc.2013.1838</mixed-citation></ref><ref id="B26"><label>26.</label><mixed-citation>Niu H., Pan Q., Xu K. (2023). Hybrid deep learning models with multi-classification investor sentiment to forecast the prices of China’s leading stocks. PLoS ONE, 18, 11, Article e0294460. DOI: 10.1371/journal.pone.0294460</mixed-citation></ref><ref id="B27"><label>27.</label><mixed-citation>Ph H., Rishad A. (2020). An empirical examination of investor sentiment and stock market volatility: evidence from India. Financial Innovations, 6, Article 34.</mixed-citation></ref><ref id="B28"><label>28.</label><mixed-citation>Phuoc T., Anh P. T.K., Tam P. H., Nguyen C. V. (2024). Applying machine learning algorithms to predict the stock price trend in the stock market — the case of Vietnam. Humanities and Social Sciences Communications, 11, Article 393. DOI: 10.1057/s41599-024-02807-x</mixed-citation></ref><ref id="B29"><label>29.</label><mixed-citation>Sarkar A., Chakraborty S., Ghosh S., Naskar S. K. (2022). Evaluating impact of social media posts by executives on stock prices. FIRE ‘22: Proceedings of the 14th Annual Meeting of the Forum for Information Retrieval Evaluation, 74–82. DOI: 10.1145/3574318.3574339</mixed-citation></ref><ref id="B30"><label>30.</label><mixed-citation>Shiller R. J. (2003). From efficient markets theory to behavioral finance. Journal of Economic Perspectives, 17, 83, Article 104.</mixed-citation></ref><ref id="B31"><label>31.</label><mixed-citation>Tallboys J., Zhu Y., Rajasegarar S. (2022). Identification of stock market manipulation with deep learning. In: International Conference on Advanced Data Mining and Applications, 408–420. Cham: Springer.</mixed-citation></ref><ref id="B32"><label>32.</label><mixed-citation>Teplova T., Tomtosov A., Sokolova T. (2022). A retail investor in a cobweb of social networks. PLoS One, 17, 12, Article e0276924.</mixed-citation></ref><ref id="B33"><label>33.</label><mixed-citation>Uslu N. C., Akal F. (2021). A machine learning approach to detection of trade-based manipulations in Borsa Istanbul. Computational Economics, 60, 1, 25–45.</mixed-citation></ref><ref id="B34"><label>34.</label><mixed-citation>Wang G., Yu G., Shen X. (2020). The effect of online investor sentiment on stock movements: An LSTM approach. Complexity, 1–11, Article 4754025.</mixed-citation></ref><ref id="B35"><label>35.</label><mixed-citation>Xu L., Xue C., Zhang J. (2024). The impact of investor sentiment on stock liquidity of listed companies in China. Investment Management and Financial Innovations, 21, 2, 1–14.</mixed-citation></ref><ref id="B36"><label>36.</label><mixed-citation>Xu Q., Wang L., Jiang C., Zhang X. (2019). A novel UMIDAS-SVQR model with mixed frequency investor sentiment for predicting stock market volatility. Expert Systems with Applications, 132, 12–27.</mixed-citation></ref></ref-list></back></article>
