Economic Activity Forecasting Based on the Sentiment Analysis of News
The outbreak of war and the earlier and ongoing COVID-19 pandemic determined the need for real-time monitoring of economic activity. The economic activity of a country can be defined in different ways. Most often, the country’s economic activity is characterized by various indicators such as the gro...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/19/3461 |
| _version_ | 1797478166991732736 |
|---|---|
| author | Mantas Lukauskas Vaida Pilinkienė Jurgita Bruneckienė Alina Stundžienė Andrius Grybauskas Tomas Ruzgas |
| author_facet | Mantas Lukauskas Vaida Pilinkienė Jurgita Bruneckienė Alina Stundžienė Andrius Grybauskas Tomas Ruzgas |
| author_sort | Mantas Lukauskas |
| collection | DOAJ |
| description | The outbreak of war and the earlier and ongoing COVID-19 pandemic determined the need for real-time monitoring of economic activity. The economic activity of a country can be defined in different ways. Most often, the country’s economic activity is characterized by various indicators such as the gross domestic product, the level of employment or unemployment of the population, the price level in the country, inflation, and other frequently used economic indicators. The most popular were the gross domestic product (GDP) and industrial production. However, such traditional tools have started to decline in modern times (as the timely knowledge of information becomes a critical factor in decision making in a rapidly changing environment) as they are published with significant delays. This work aims to use the information in the Lithuanian mass media and machine learning methods to assess whether these data can be used to assess economic activity. The aim of using these data is to determine the correlation between the usual indicators of economic activity assessment and media sentiments and to forecast traditional indicators. When evaluating consumer confidence, it is observed that the forecasting of this economic activity indicator is better based on the general index of negative sentiment (comparisons with univariate time series). In this case, the average absolute percentage error is 1.3% lower. However, if all sentiments are included in the forecasting instead of the best one, the forecasting is worse and in this case the MAPE is 5.9% higher. It is noticeable that forecasting the monthly and annual inflation rate is thus best when the overall negative sentiment is used. The MAPE of the monthly inflation rate is as much as8.5% lower, while the MAPE of the annual inflation rate is 1.5% lower. |
| first_indexed | 2024-03-09T21:28:08Z |
| format | Article |
| id | doaj.art-01ad4a5491aa4c53bb7d477a0f605732 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T21:28:08Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-01ad4a5491aa4c53bb7d477a0f6057322023-11-23T21:01:54ZengMDPI AGMathematics2227-73902022-09-011019346110.3390/math10193461Economic Activity Forecasting Based on the Sentiment Analysis of NewsMantas Lukauskas0Vaida Pilinkienė1Jurgita Bruneckienė2Alina Stundžienė3Andrius Grybauskas4Tomas Ruzgas5Department of Applied Mathematics, Faculty of Mathematics and Natural Sciences, Kaunas University of Technology, 44249 Kaunas, LithuaniaSchool of Economics and Business, Kaunas University of Technology, 44249 Kaunas, LithuaniaSchool of Economics and Business, Kaunas University of Technology, 44249 Kaunas, LithuaniaSchool of Economics and Business, Kaunas University of Technology, 44249 Kaunas, LithuaniaSchool of Economics and Business, Kaunas University of Technology, 44249 Kaunas, LithuaniaDepartment of Applied Mathematics, Faculty of Mathematics and Natural Sciences, Kaunas University of Technology, 44249 Kaunas, LithuaniaThe outbreak of war and the earlier and ongoing COVID-19 pandemic determined the need for real-time monitoring of economic activity. The economic activity of a country can be defined in different ways. Most often, the country’s economic activity is characterized by various indicators such as the gross domestic product, the level of employment or unemployment of the population, the price level in the country, inflation, and other frequently used economic indicators. The most popular were the gross domestic product (GDP) and industrial production. However, such traditional tools have started to decline in modern times (as the timely knowledge of information becomes a critical factor in decision making in a rapidly changing environment) as they are published with significant delays. This work aims to use the information in the Lithuanian mass media and machine learning methods to assess whether these data can be used to assess economic activity. The aim of using these data is to determine the correlation between the usual indicators of economic activity assessment and media sentiments and to forecast traditional indicators. When evaluating consumer confidence, it is observed that the forecasting of this economic activity indicator is better based on the general index of negative sentiment (comparisons with univariate time series). In this case, the average absolute percentage error is 1.3% lower. However, if all sentiments are included in the forecasting instead of the best one, the forecasting is worse and in this case the MAPE is 5.9% higher. It is noticeable that forecasting the monthly and annual inflation rate is thus best when the overall negative sentiment is used. The MAPE of the monthly inflation rate is as much as8.5% lower, while the MAPE of the annual inflation rate is 1.5% lower.https://www.mdpi.com/2227-7390/10/19/3461clusteringeconomic activitynatural language processingNLPtransformersBERT |
| spellingShingle | Mantas Lukauskas Vaida Pilinkienė Jurgita Bruneckienė Alina Stundžienė Andrius Grybauskas Tomas Ruzgas Economic Activity Forecasting Based on the Sentiment Analysis of News Mathematics clustering economic activity natural language processing NLP transformers BERT |
| title | Economic Activity Forecasting Based on the Sentiment Analysis of News |
| title_full | Economic Activity Forecasting Based on the Sentiment Analysis of News |
| title_fullStr | Economic Activity Forecasting Based on the Sentiment Analysis of News |
| title_full_unstemmed | Economic Activity Forecasting Based on the Sentiment Analysis of News |
| title_short | Economic Activity Forecasting Based on the Sentiment Analysis of News |
| title_sort | economic activity forecasting based on the sentiment analysis of news |
| topic | clustering economic activity natural language processing NLP transformers BERT |
| url | https://www.mdpi.com/2227-7390/10/19/3461 |
| work_keys_str_mv | AT mantaslukauskas economicactivityforecastingbasedonthesentimentanalysisofnews AT vaidapilinkiene economicactivityforecastingbasedonthesentimentanalysisofnews AT jurgitabruneckiene economicactivityforecastingbasedonthesentimentanalysisofnews AT alinastundziene economicactivityforecastingbasedonthesentimentanalysisofnews AT andriusgrybauskas economicactivityforecastingbasedonthesentimentanalysisofnews AT tomasruzgas economicactivityforecastingbasedonthesentimentanalysisofnews |