Building a high-frequency media indicator of regional economic activity based on analysis of media publications using large language models

Section: Artificial Intelligence in Media and Communication Studies

The inherent publication lags in official statistical releases have precipitated a growing scholarly and practical interest in alternative data sources for economic assessment. Among these, the vast corpus of textual data from media outlets, processed through Large Language Models (LLMs), presents a significant opportunity. This study aims to develop a media-based indicator of economic activity for a constituent entity of the Russian Federation by analyzing regional news publications with LLMs. The empirical foundation of this research comprises a corpus of texts from online media spanning the period 2021–2025. The methodological framework consists of several sequential stages: (i) the compilation and preprocessing of a regional news publicati on database; (ii) the thematic classification of texts according to aggregated economic sectors employing a zeroshot classification paradigm; (iii) the extraction of economic sentiment from the news articles using the GigaChat large language model; and (iv) the construction of an aggregated media indicator. The resulting output is an integral media indicator of economic dynamics, designated as the IBVEDMedia index. A comparative analysis with the official Index of Output of Goods and Services for Basic Economic Activities reveals a statistically significant correlation between the two time series. This finding suggests that the news flow from regional media sources encapsulates substantial information pertinent to the current state of the regional economy. The proposed media indicator can be considered a composite economic sentiment indicator, serving as a valuable complement to traditional official statistics. The validation of its real-time operational properties is a subject for future research.

DOI: 10.55959/msu.vestnik.journ.3.2026.328

References:

Acedański J. (2024) Disaggregation and Nowcasting of Regional GDP Series with a Simple Smoothing Algorithm. Journal of Official Statistics 40 (4): 508–529. DOI: 10.1177/0282423X241277716.

Alam M. J., Boyle S., Li H., Sekhposyan T. (2026) ChatMacro: Evaluating Inflation Forecasts of Generative AI. Working Paper Series 4. DOI: 10.24148/wp2026-04. Available at: https://ideas.repec.org/p/fip/fedfwp/102407.html (accessed: 24.02.2026).

Boyko V., Kislyak N., Nikitin M., Oborin O. (2020) Methods for Estimating the Gross Regional Product Leading Indicator. Russian Journal of Money and Finance 79 (3): 3–29. DOI: 10.31477/rjmf.202003.03.

Bybee L. (2023) Surveying Generative AI's Economic Expectations. arXiv. DOI: 10.48550/arXiv.2305.02823. Available at: https://arxiv.org/abs/2305.02823 (accessed: 17.01.2026).

Clements M. P., Galvão A. B. (2009) Forecasting US Output Growth Using Leading Indicators: An Appraisal Using MIDAS Models. Journal of Applied Econometrics 24 (7): 1187–1206. DOI: 10.1002/jae.1075.

Dahlhaus T., Guénette J.-D., Vasishtha G. (2017) Nowcasting BRIC+M in Real Time. International Journal of Forecasting 33 (4): 915–935. DOI: 10.1016/j.ijforecast.2017.05.002.

Eliseev A. (2025) Nowcasting Russian GDP in a Mixed-Frequency DSGE Model with a Panel of Non-Modelled Variables. Russian Journal of Money and Finance 84 (3): 63–93.

Evstigneeva A., Karpov D. (2023) Vliyanie negativnykh novostey na vospriyatie inflyatsii naseleniem [Impact of Negative News on Households' Perception of Inflation]. Bank of Russia Working Papers No 111. Available at: https://cbr.ru/Content/Document/File/144918/wp_111.pdf (accessed: 20.11.2025). (In Russian)

Fokin N. D. (2023) Naukasting i prognozirovanie osnovnykh rossiyskikh makroekonomicheskikh pokazateley s pomoshch'yu MFBVAR-modeli [Nowcasting and forecasting key Russian macroeconomic variables with the MFBVAR model]. Economic Policy 18 (3): 110–135. DOI: 10.18288/1994-5124-2023-3-110-135 (In Russian)

Fosten J., Greenaway-McGrevy R. (2022) Panel data nowcasting. Econometric Reviews 41 (7): 675–696. DOI: 10.1080/07474938.2021.2017670.

Gareev M. Yu., Polbin A. V. (2022) Naukasting: otsenka izmeneniya klyuchevykh makroekonomicheskikh pokazateley s ispol'zovaniem metodov mashinnogo obucheniya [Nowcasting Russia's key macroeconomic variables using machine learning]. Voprosy Ekonomiki 8: 133–157. DOI: 10.32609/0042-8736-2022-8-133-157 (In Russian)

Ghysels E. (2016) Macroeconomics and the reality of mixed frequency data. Journal of Econometrics 193 (2): 294–314. DOI: 10.1016/j.jeconom.2016.04.008.

Koop G., Korobilis D., Pettenuzzo D. (2019) Bayesian Compressed Vector Autoregressions. Journal of Econometrics 210 (1): 135–154. DOI: 10.1016/j.jeconom.2018.11.009.

Lazaryan S. S., German N. E. (2018) Prognozirovanie tekushchey dinamiki VVP na osnove dannykh poiskovykh zaprosov [Forecasting current GDP dynamics based on search query data]. Financial Journal 6: 83–94. DOI: 10.31107/2075-1990-2018-6-83-94 (In Russian)

Makeeva N. M., Stankevich I. P. (2022) Naukasting elementov ispol'zovaniya VVP Rossii [Nowcasting of the components of Russian GDP]. HSE Economic Journal 4: 598–622. DOI: 10.17323/1813-8691-2022-26-4-598-622 (In Russia n)

Mikosch H., Solanko L. (2019) Forecasting Quarterly Russian GDP Growth with Mixed-Frequency Data. Russian Journal of Money and Finance 78 (1): 19–35. DOI: 10.31477/rjmf.201901.19.

Porshakov A. S., Ponomarenko A. A., Sinyakov A. A. (2016) Otsenka i prognozirovanie VVP Rossii s pomoshch'yu dinamicheskoy faktornoy modeli [Estimation and forecasting of Russia's GDP using a dynamic factor model]. Journal of the New Economic Association 2 (30): 60–76. DOI: 10.31737/2221-2264-2016-30-2-3 (In Russian)

Richardson A., van Florenstein Mulder T., Vehbi T. (2021) Nowcasting GDP using Machine-Learning Algorithms: A Real-Time Assessment. International Journal of Forecasting 37 (2): 941–948. DOI: 10.1016/j.ijforecast.2020.10.005.

Seleznev S., Shibitov D., Yakovleva K., Vlasov S. et al. (2021) Novaya metodologiya novostnogo indeksa [New News Index Methodology]. Bank of Russia Working Papers. Available at: https://cbr.ru/Collection/Collection/File/35503/index_2107.pdf (accessed: 26.11.2025). (In Russian)

Shulyak E. (2022) Macroeconomic Forecasting Using Data from Social Media. Russian Journal of Money and Finance 81 (4): 86–112.

Stankevich I. P. (2023) Primenenie MIDAS-modeley s markovskim pereklyucheniem dlya naukastinga VVP i ego komponentov [Application of MIDAS models with Markov switching for nowcasting GDP and its components]. Applied Econometrics 2: 122–143. DOI: 10.22394/1993-7601-2023-70-122-143 (In Russian)

Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A. N., Kaiser L., Polosukhin I. (2017) Attention Is All You Need. arXiv. DOI: 10.48550/arXiv.1706.03762. Available at: https://arxiv.org/abs/1706.03762 (accessed: 24.12.2025).

Yakovleva K. (2018) Text Mining-based Economic Activity Estimation. Russian Journal of Money and Finance 77 (4): 26–41. DOI: 10.31477/rjmf.201804.26.

Zhang Q., Ni H., Xu H. (2023) Nowcasting Chinese GDP in a Data-Rich Environment: Lessons from Machine Learning Algorithms. Economic Modelling 122: 106204. DOI: 10.1016/j.econmod.2023.106204.

Zubarev A. V., Rybak K. S. (2021) Naukasting VVP: dinamicheskaya faktornaya model' i ofitsial'nye prognozy [Nowcasting GDP: dynamic factor model and official forecasts]. Economic Development of Russia 12: 34–40 (In Russian)