ASSESSMENT OF THE IMPACT OF MEDIA NEWS BACKGROUNDS ON INFLATION IN RUSSIA

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 economi...

Полное описание

Сохранить в:

Библиографические подробности
Главные авторы:	Kunitsyna, N. N., Куницына, Н. Н.
Формат:	Статья
Язык:	English
Опубликовано:	MSU Publishing House 2025
Темы:	Bert Text analysis Consumer price index Inflation News background Nlp Transformers
Online-ссылка:	https://dspace.ncfu.ru/handle/123456789/31673
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!

id	ir-123456789-31673
record_format	dspace
spelling	ir-123456789-316732025-08-01T12:34:57Z ASSESSMENT OF THE IMPACT OF MEDIA NEWS BACKGROUNDS ON INFLATION IN RUSSIA Kunitsyna, N. N. Куницына, Н. Н. Bert Text analysis Consumer price index Inflation News background Nlp Transformers 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. 2025-08-01T12:33:58Z 2025-08-01T12:33:58Z 2025 Статья Metel, Y. A., Kunitsyna, N. N. ASSESSMENT OF THE IMPACT OF MEDIA NEWS BACKGROUNDS ON INFLATION IN RUSSIA // VESTNIK MOSKOVSKOGO UNIVERSITETA. SERIYA 10. ZHURNALISTIKA. - 2025. - 2. - pp. 3 - 32. - DOI: 10.55959/msu.vestnik.journ.2.2025.332 https://dspace.ncfu.ru/handle/123456789/31673 en VESTNIK MOSKOVSKOGO UNIVERSITETA. SERIYA 10. ZHURNALISTIKA application/pdf application/pdf MSU Publishing House
institution	СКФУ
collection	Репозиторий
language	English
topic	Bert Text analysis Consumer price index Inflation News background Nlp Transformers
spellingShingle	Bert Text analysis Consumer price index Inflation News background Nlp Transformers Kunitsyna, N. N. Куницына, Н. Н. ASSESSMENT OF THE IMPACT OF MEDIA NEWS BACKGROUNDS ON INFLATION IN RUSSIA
description	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.
format	Статья
author	Kunitsyna, N. N. Куницына, Н. Н.
author_facet	Kunitsyna, N. N. Куницына, Н. Н.
author_sort	Kunitsyna, N. N.
title	ASSESSMENT OF THE IMPACT OF MEDIA NEWS BACKGROUNDS ON INFLATION IN RUSSIA
title_short	ASSESSMENT OF THE IMPACT OF MEDIA NEWS BACKGROUNDS ON INFLATION IN RUSSIA
title_full	ASSESSMENT OF THE IMPACT OF MEDIA NEWS BACKGROUNDS ON INFLATION IN RUSSIA
title_fullStr	ASSESSMENT OF THE IMPACT OF MEDIA NEWS BACKGROUNDS ON INFLATION IN RUSSIA
title_full_unstemmed	ASSESSMENT OF THE IMPACT OF MEDIA NEWS BACKGROUNDS ON INFLATION IN RUSSIA
title_sort	assessment of the impact of media news backgrounds on inflation in russia
publisher	MSU Publishing House
publishDate	2025
url	https://dspace.ncfu.ru/handle/123456789/31673
work_keys_str_mv	AT kunitsynann assessmentoftheimpactofmedianewsbackgroundsoninflationinrussia AT kunicynann assessmentoftheimpactofmedianewsbackgroundsoninflationinrussia
_version_	1842245702042779648

ASSESSMENT OF THE IMPACT OF MEDIA NEWS BACKGROUNDS ON INFLATION IN RUSSIA

Схожие документы