Субботовский Д.А., Павлова Т.И., Трескова Е.А., Нагапетян А.Р. Моделирование влияния новостного сентимента из англоязычных источников на волатильность фондовых индексов Московской биржи

Научная статья
УДК 330.43:336.7
https://doi.org/10.24158/tipor.2026.2.14
 

Моделирование влияния новостного сентимента из англоязычных источников

на волатильность фондовых индексов Московской биржи

 
Дмитрий Андреевич Субботовский¹, Татьяна Ивановна Павлова²,
Елена Андреевна Трескова³, Артур Рубикович Нагапетян^4
1,2,3,4Дальневосточный федеральный университет, Владивосток, Россия
¹subbotovskii.da@dvfu.ru, https://orcid.org/0009-0001-1421-2157
²Tipavlova@nes.ru, https://orcid.org/0009-0006-0350-2622
³treskova.ea@dvfu.ru, https://orcid.org/0009-0002-7141-9266
⁴nagapetyan_ar@dvfu.ru,https://orcid.org/0000-0002-7885-2460
 
Аннотация. В статье исследуется влияние новостного сентимента из англоязычных источников на реализованную волатильность фондовых индексов Московской биржи в период структурных изменений 2020–2024 гг. Анализ выполнен на основе высокочастотных данных по шести индексам (IMOEX, MOEXOG, MOEXMM, MOEXFN, MOEXCN, MOEXTL) и массиву новостей портала The Guardian (11 800 новостей на индекс), с применением модели FinBERT рассчитаны авторские метрики сентимента, на базе которых осуществлено прогнозирование с использованием модифицированных моделей HAR-RV. Сравнение прогнозной силы проведено процедурой MCS. Результаты показали, что до февраля 2022 г. учет сентимента повышал качество прогнозов, после введения санкций его влияние снижается. Выявлены стабильно положительная роль индекса RVI и защитная роль нефти и золота.
Ключевые слова:реализованная волатильность, новостной сентимент, HAR-RV, FinBERT, фондовые индексы, Московская биржа, Model Confidence Set
Финансирование: инициативная работа.
Для цитирования: Субботовский Д.А., Павлова Т.И., Трескова Е.А., Нагапетян А.Р. Моделирование влияния новостного сентимента из англоязычных источников на волатильность фондовых индексов Московской биржи // Теория и практика общественного развития. 2026. № 2. С. 117–124. https://doi.org/10.24158/tipor.2026.2.14.
 
Original article
 

Modeling the Impact of News Sentiment from English-Language Sources

on the Volatility of Moscow Exchange Stock Indices

 
Dmitry A. Subbotovsky¹, Tatyana I. Pavlova²,
Elena A. Treskova³, Artur R. Nagapetyan^4
1,2,3,4Far Eastern Federal University, Vladivostok, Russia
¹subbotovskii.da@dvfu.ru, https://orcid.org/0009-0001-1421-2157
²Tipavlova@nes.ru, https://orcid.org/0009-0006-0350-2622
³treskova.ea@dvfu.ru, https://orcid.org/0009-0002-7141-9266
⁴nagapetyan_ar@dvfu.ru, https://orcid.org/0000-0002-7885-2460
 
Abstract. The article examines the impact of English-language news sentiment on the realized volatility of Moscow Exchange indices in 2020–2024. Based on high-frequency data for six indices and news from The Guardian (11,800 messages per index), author’s sentiment metrics were calculated using the FinBERT model. Forecasting was performed using modified HAR-RV models, with predictive power compared by the MCS procedure. The results showed that before February 2022, sentiment inclusion improves forecast quality; after sanctions, its influence decreases. A consistently positive role of the RVI index and the safe-haven role of oil and gold were identified.
Keywords: realized volatility, news sentiment, HAR-RV, FinBERT, stock indices, Moscow Exchange, Model Confidence Set
Funding: Independent work.
For citation: Subbotovsky, D.A., Pavlova, T.I., Treskova, E.A. & Nagapetyan, A.R. (2026) Modeling the Impact of News Sentiment from English-Language Sources on the Volatility of Moscow Exchange Stock Indices. Theory and Practice of Social Development. (2), 117–124. Available from: doi:10.24158/tipor.2026.2.14 (In Russian).

© Субботовский Д.А., Павлова Т.П., Трескова Е.А., Нагапетян А.Р., 2026

Список источников:
 
Аганин А.Д. Сравнение GARCH и HAR-RV моделей для прогноза реализованной волатильности на российском рынке // Прикладная эконометрика. 2017. № 4 (48). С. 63–84.
Сентимент частных инвесторов в объяснении различий в биржевых характеристиках акций российского рынка / Т.В. Теплова, Т.В. Соколова, А.Ф. Томтосов, Д.В. Бучко, Д.Д. Никулин // Журнал Новой экономической ассоциации. 2022. № 1 (53). С. 53–84. https://doi.org/10.31737/2221-2264-2022-53-1-3.
Сидоров С.П., Дате П., Балаш В.А. Использование данных новостной аналитики в GARCH моделях // Прикладная эконометрика. 2013. № 1 (29). С. 82–96.
A comparative study on effect of news sentiment on stock price prediction with deep learning architecture / K.R. Dahal, N.R. Pokhrel, S. Gaire, S. Mahatara, R.P. Joshi, A. Gupta, H.R. Banjade, J. Joshi // PLoS ONE. 2023. Vol. 18, no. 4. P. e0284695. https://doi.org/10.1371/journal.pone.0284695.
Andersen T.G., Bollerslev T., Diebold F.X., Ebens H. The distribution of realized stock return volatility // Journal of Financial Economics. 2001. Vol. 61, no. 1. P. 43–76. https://doi.org/10.1016/S0304-405X(01)00055-1.
Bollerslev T. Generalized autoregressive conditional heteroskedasticity // Journal of Econometrics. 1986. Vol. 31. P. 307–327. https://doi.org/10.1016/0304-4076(86)90063-1.
Buddiga S.K.P. Deciphering market sentiment: Methodological insights and applications with FinBERT sentiment analysis // International Journal of Financial Data Science (IJFDS). 2024. Vol. 2, no. 1. P. 17–22. https://doi.org/10.17605/OSF.IO/9DK5B.
Corsi F. A simple approximate long-memory model of realized volatility // Journal of Financial Econometrics. 2009. Vol. 7, no. 2. P. 174–196. https://doi.org/10.1093/jjfinec/nbp001.
Craioveanu M., Hillebrand E. Why it is ok to use the HAR-RV(1, 5, 21) model // Working Papers University of Central Missouri. 2012. No. 1201.
Engle R.F. Autoregressive conditional heteroskedasticity with estimates of the variance of United Kingdom inflation // Econometrica. 1982. Vol. 50, no. 4. P. 987–1008. https://doi.org/10.2307/1912773.
Exchange rate, gold price, and stock market nexus: A quantile regression approach / R. Ali, I.U. Mangla, R.U. Rehman, W. Xue, M.A. Naseem, M.I. Ahmad // Risks. 2020. Vol. 8, no. 3. P. 86. https://doi.org/10.3390/risks8030086.
Fama E.F. Efficient capital markets: A review of theory and empirical work // The Journal of Finance. 1970. Vol. 25, no. 2. P. 383–417.
Fazlija B., Harder P. Using financial news sentiment for stock price direction prediction // Mathematics. 2022. Vol. 10, no. 13. P. 2156. https://doi.org/10.3390/math10132156.
Gao Y., Zhao C., Sun B., Zhao W. Effects of investor sentiment on stock volatility: New evidences from multi-source data in China’s green stock markets // Financial Innovation. 2022. Vol. 8. P. 77. https://doi.org/10.1186/s40854-022-00381-2.
Hansen P.R., Lunde A., Nason J.M. The model confidence set // Econometrica. 2011. Vol. 79, no. 2. P. 453–497. https://doi.org/10.3982/ECTA5771.
Joshi K., Bharathi N., Rao J. Stock trend prediction using news sentiment analysis // International Journal of Computer Science and Information Technology. 2016. Vol. 8, no. 3. P. 67–76. https://doi.org/10.5121/ijcsit.2016.8306.
Kahneman D., Tversky A. Prospect theory: An analysis of decision under risk // Econometrica. 1979. Vol. 47, no. 2. P. 263–292.
Lahaye J., Shaw P. Can we reject linearity in an HAR-RV model for the S&P 500? Insights from a nonparametric HAR-RV // Economics Letters. 2014. Vol. 125, no. 1. P. 43–46. https://doi.org/10.1016/j.econlet.2014.07.003.
Liu W., Tang M., Zhao P. The dynamic impact of investor climate sentiment on the crude oil futures market: Evidence from the Chinese market // PLoS ONE. 2025. Vol. 20, no. 2. P. e0314579. https://doi.org/10.1371/journal.pone.0314579.
Torre-Torres O.V. De la, Aguilasocho-Montoya D., Bollain-Parra L., Durán-Sánchez A. The impact of COVID-19, news and investor sentiment in European stock pricing. A regional, country, and economic sector review // Revista Portuguesa de Estudos Regionais. 2022. No. 60. https://doi.org/10.59072/rper.vi60.69.
Wan J., Han L., Wu Y. Time-frequency volatility spillovers between CBDC uncertainty and cryptocurrencies // Finance Research Letters. 2025. Vol. 74. P. 106763. https://doi.org/10.1016/j.frl.2025.106763.
 
References:
 
Aganin, A.G. (2017) Forecast comparison of volatility models on Russian stock market. Applied Econometrics. (4), 63–84. (In Russian)
Ali, R., Mangla, I.U., Rehman, R.U., Xue, W., Naseem, M.A. & Ahmad, M.I. Exchange rate, gold price, and stock market nexus: A quantile regression approach. Risks. 8 (3), 86. Available from: doi:10.3390/risks8030086.
Andersen, T.G., Bollerslev, T., Diebold, F.X. & Ebens, H. (2001) The distribution of realized stock return volatility. Journal of Financial Economics. 31 (1), 43–76. Available from: doi:10.1016/S0304-405X(01)00055-1.
Bollerslev, T. (1986) Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics. 31, 307–327. Available from: doi:10.1016/0304-4076(86)90063-1.
Buddiga, S.K.P. (2024) Deciphering market sentiment: Methodological insights and applications with FinBERT sentiment analysis. International Journal of Financial Data Science (IJFDS). 2 (1), 17–22. Available from: doi:10.17605/OSF.IO/9DK5B.
Corsi, F. (2009) A simple approximate long-memory model of realized volatility. Journal of Financial Econometrics. 7 (2), 174–196. Available from: doi:10.1093/jjfinec/nbp001.
Craioveanu, M. & Hillebrand, E. (2012) Why it is ok to use the HAR-RV(1, 5, 21) model. Working Papers University of Central Missouri. (1201).
Dahal, K.R., Pokhrel, N.R., Gaire, S., Mahatara, S., Joshi, R.P., Gupta, A., Banjade, H.R. & Joshi, J. (2023) A comparative study on effect of news sentiment on stock price prediction with deep learning architecture. PLoS ONE. 18 (4), e0284695. Available from: doi:10.1371/journal.pone.0284695.
Engle, R.F. (1982) Autoregressive conditional heteroskedasticity with estimates of the variance of United Kingdom inflation. Econometrica. 50 (4), 987–1008. Available from: doi:10.2307/1912773.
Fama, E.F. (1970) Efficient capital markets: A review of theory and empirical work. The Journal of Finance. 25 (2), 383–417.
Fazlija, B. & Harder, P. (2022) Using financial news sentiment for stock price direction prediction. Mathematics. 10 (13), 2156. Available from: doi:10.3390/math10132156.
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, 77. Available from: doi:10.1186/s40854-022-00381-2.
Hansen, P.R., Lunde, A. & Nason, J.M. (2011) The model confidence set. Econometrica. 2011. 79 (2), 453–497. Available from: doi:10.3982/ECTA5771.
Joshi, K., Bharathi, N. & Rao, J. (2016) Stock trend prediction using news sentiment analysis. International Journal of Computer Science and Information Technology. 8 (3), 67–76. Available from: doi:10.5121/ijcsit.2016.8306.
Kahneman, D. & Tversky, A. (1979) Prospect theory: An analysis of decision under risk. Econometrica. 47 (2), 263–292.
Lahaye, J. & Shaw, P. (2014) Can we reject linearity in an HAR-RV model for the S&P 500? Insights from a nonparametric HAR-RV. Economics Letters. 125 (1), 43–46. Available from: doi:10.1016/j.econlet.2014.07.003.
Liu, W., Tang, M. & Zhao, P. (2025) The dynamic impact of investor climate sentiment on the crude oil futures market: Evidence from the Chinese market. PLoS ONE. 20 (2), e0314579. Available from: doi:10.1371/journal.pone.0314579.
Sidorov, S., Date, P. & Balash, V.A. (2013) Using news analytics data in GARCH models. Applied Econometrics. (1), 82–96. (In Russian)
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), 53–84. Available from: doi:10.31737/2221-2264-2022-53-1-3. (In Russian)
Torre-Torres, O.V. De la, Aguilasocho-Montoya, D., Bollain-Parra, L. & Durán-Sánchez, A. (2022) The impact of COVID-19, news and investor sentiment in European stock pricing. A regional, country, and economic sector review. Revista Portuguesa de Estudos Regionais. (60). Available from: doi:10.59072/rper.vi60.69.
Wan, J., Han, L. & Wu, Y. (2025) Time-frequency volatility spillovers between CBDC uncertainty and cryptocurrencies. Finance Research Letters. 74, 106763. Available from: doi:10.1016/j.frl.2025.106763.