Assessment of the impact of media news backgrounds on inflation in Russia

Section: Sociology of Journalism

Given the growing number and variety of information flows, the influence of the media on public sentiment, the news background, as a key element of media information, directly affects economic decisions, and the analysis of its dynamics in real time can significantly increase the accuracy of economic forecasts and models. The article studied the impact of the news background contained in media publications on the prices and inflation level. The methodological tools proposed by the authors make it possible not only to analyze inflationary processes, but also to predict their dynamics taking into account the media context. Processing 147 thousand news articles by using a pre-trained neural network from Microsoft made it possible to select 3.5 thousand news about inflation and prices, dividing them into “proinflationary” and “disinflationary”. To form training and test samples, a connection to the GigaChat neural network is implemented. The inflation tonality of the marked news was simulated by pre-processing using the TF-IDF method and using logistic regression, Naive Bayesian classifier, Random Forest and CatBoost, as well as by additional training (fine-tuning) of neural networks based on the BERT architecture, pre-trained in Russian. The methodological basis was made up of methods for parsing html sites, natural language processing (NLP), deep neural network architecture, and regression algorithms. As a result, we have the inflation background index contained in the Russian media publications, with high accuracy describing the “shock” events in the economy. The findings can be used to fine-tune economic models and create forecasting tools, highlighting the importance of media content in assessing the economic situation.

DOI: 10.55959/msu. vestnik.journ.2.2025.332

References:

Baybuza I. (2018) Prognozirovanie inflyatsii s pomoshch’yu metodov mashinnogo obucheniya [Inflation Forecasting Using Machine Learning Methods]. Russian Journal of Money and Finance 77(4): 42–59. (In Russian)

Choi E., Bahadori M. T., Schuetz A., Stewart W. F., Sun J. (2016) Doctor AI: Predicting Clinical Events via Recurrent Neural Networks. JMLR Workshop and Conference Proceedings 56: 301–318. Available at: https://doi.org/10.48550/ arXiv.1511.05942 

Christopher D. M., Raghavan P., Schütze H. (2008) Introduction to information retrieval. Cambridge: Cambridge University Press. 482 p.

Chung H. W., Fevry T., Tsai H., Johnson M., Ruder S. (2021) Rethinking embedding coupling in pre-trained language models. International Conference on Learning Representations. Available at: https://arxiv.org/abs/2010.12821 (accessed: 10.03.2024).

Conneau A., Wu S., Li H., Zettlemoyer L., Stoyanov V. (2020) Emerging Cross-lingual Structure in Pretrained Language Models. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Рp. 6022–6034. DOI: 10.18653/v1/2020.acl-main.536 

Devlin J., Chang M., Lee K., Toutanova K. (2019) BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Volume 1 (Long and Short Papers). P. 4171–4186. DOI: 10.18653/v1/N19-1423.

Dzhunkeev U. (2024) Prognozirovanie inflyatsii v Rossii na osnove gradientnogo bustinga i nejronnykh setey [Forecasting Inflation in Russia Using Gradient Boosting and Neural Networks]. Russian Journal of Money and Finance 83 (1): 53–76. (In Russian)

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 111. Available at: https:// cbr.ru/Content/Document/File/144918/wp_111.pdf (accessed: 03.03.2024). (In Russian)

Fawcett T. (2006) An introduction to ROC analysis. Pattern Recognition Letters 27 (8): 861–874.

Fedorova E. A., Hrustova L. E. (2023) Vliyanie novostey o COVID-19 na dinamiku rossiyskogo fondovogo rynka [Impact of news about COVID-19 on the dynamics of the Russian stock market]. Finance and Credit 29 (11): 2412– 2438. (In Russian).

Gavrilov V., Ivanov M. A., Klachkova O. A., Korolev V. Yu., Roshhina Ya. A. (2022) Vliyanie tematicheskikh novostnykh potokov na komponenty volatil’nosti fondovogo rynka Rossii [Impact of thematic news streams on Russian stock market volatility components]. The Bulletin of the Institute of Economics of the Russian Academy of Sciences 2: 93–109. (In Russian)

He P., Gao J., Chen W. (2021) DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing. Arxiv. Available at: https://arxiv.org/pdf/2111.09543.pdf (accessed: 17.03.2024).

Howard J., Ruder S. (2018) Universal Language Model Fine-tuning for Text Classification. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne, Australia: Association for Computational Linguistics. Рp. 328–339. DOI: 10.18653/v1/P18-1031.

Pavlov E. (2020) Prognozirovanie inflyatsii v Rossii s pomoshch’yu neyronnykh setey [Forecasting Inflation in Russia Using Neural Networks]. Russian Journal of Money and Finance 79 (1): 57–73. (In Russian)

Seleznev S., Shibitov D., Yakovleva K., Vlasov S., Chernjad’ev D. (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: 10.03.2024) (In Russian).

Shliazhko O., Fenogenova A., Tikhonova M., Mikhailov V., Kozlova A., Shavrina T. (2022) mGPT: Few-Shot Learners Go Multilingual. Arxiv. Available at: https://arxiv.org/pdf/2204.07580.pdf (accessed: 17.03.2024).

Sinha K., Jia R., Hupkes D., Pineau J., Williams A., Kiela D. (2021) Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little. Available at: https://arxiv.org/pdf/2109.03564. pdf (accessed: 17.03.2024).

Sun Y., Zheng Y., Hao C., Qiu H. (2022) NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task – Next Sentence Prediction. Arxiv. Available at: https://arxiv.org/pdf/2104.06644.pdf (accessed: 17.03.2024).

Valouet T., Al-Memar M., Fourie H., Bobdiwala S., Saso S., Pipi M., Stalder C., Bennett P., Timmerman D., Bourte T. and De Moor B. (2022) Gradient boosted trees with individual explanations: An alternative to logistic regression for predicting viability in the first trimester of pregnancy. Computer Methods and Programs in Biomedicine 213: 106520.

Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A. N., Kaiser L., Polosukhin I. (2017) Attention Is All You Need. Arxiv. Available at: https://arxiv.org/abs/1706.03762 (accessed: 17.03.2024).

Williams A., Nangia N., Bowman S.R. (2017) A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference. Arxiv. Available at: https://doi.org/10.48550/arXiv.1704.05426 (accessed: 10.03.2024).

Wu Y., Schuster M., Chen Zh., Le Q. V., Norouzi M., Macherey W., Krikun M., Cao Yu., Gao Q., Macherey K., Klingner J., Shah A., Johnson M., Liu X., Kaiser L., Gouws S., Kato Y., Kudo T., Kazawa H., Stevens K., Kurian G., Patil N., Wang W., Young C., Smith J., Riesa J., Rudnick A., Vinyals O., Corrado G., Hughes M., Dean J. (2016) Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine. Arxiv. Available at: https://arxiv.org/abs/1609.08144 (accessed: 14.03.2024).

Yakovleva K. (2018) Otsenka ekonomicheskoy aktivnosti na osnove tekstovogo analiza [Assessment of economic activity based on text analysis]. Russian Journal of Money and Finance 77(4): 26–41. (In Russian)

To cite this article: Metel Yu. A., Kunitsyna N. N. (2025) Otsenka vliyaniya novostnogo fona v SMI na uroven’ inflyatsii v Rossii [Assessment of the impact of media news backgrounds on inflation in Russia]. Vestnik Moskovskogo Universiteta. Seriya 10. Zhurnalistika 2: 3–32. DOI: 10.55959/msu.vestnik.journ.2.2025.332