Evaluation of News Sentiment in Economic Activity Forecasting

Engineering Proceedings

article

Mantas Lukauskas¹  Vaida Pilinkienė²  Jurgita Bruneckienė²  Alina Stundžienė²  Andrius Grybauskas²  Tomas Ruzgas¹ 

[1] Department of Applied Mathematics, Faculty of Mathematics and Natural Sciences, Kaunas University of Technology;School of Economics and Business, Kaunas University of Technology

关键词: clustering;    economic activity;    natural language processing;    NLP;    transformers;    BERT;    forecasting;    nowcasting;    economic sentiment68T50;    91B84;    62H30;   

DOI  :  10.3390/ASEC2022-13790

来源: mdpi

【 摘 要 】

Featured ApplicationThe analysis of news sentiments presented in this article can be used for various research and practical applications. In this study, news sentiment analysis was used in order to perform more accurate forecasting of economic indicators. Based on the results obtained in the study, it can be seen that the negative sentiment index is strongly linked to economic indicators. Based on the value of the sentiment, for this reason, economic activity and individual indicators of economic activity can be predicted. It can be used in the activities of various decision-makers, banks, and state institutions.

【 授权许可】

Unknown