A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series Forecasting
In practice, time series forecasting involves the creation of models that generalize data from past values and produce future predictions. Moreover, regarding financial time series forecasting, it can be assumed that the procedure involves phenomena partly shaped by the social environment. Thus, the...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/12/1603 |
| _version_ | 1797504900855234560 |
|---|---|
| author | Charalampos M. Liapis Aikaterini Karanikola Sotiris Kotsiantis |
| author_facet | Charalampos M. Liapis Aikaterini Karanikola Sotiris Kotsiantis |
| author_sort | Charalampos M. Liapis |
| collection | DOAJ |
| description | In practice, time series forecasting involves the creation of models that generalize data from past values and produce future predictions. Moreover, regarding financial time series forecasting, it can be assumed that the procedure involves phenomena partly shaped by the social environment. Thus, the present work is concerned with the study of the use of sentiment analysis methods in data extracted from social networks and their utilization in multivariate prediction architectures that involve financial data. Through an extensive experimental process, 22 different input setups using such extracted information were tested, over a total of 16 different datasets, under the schemes of 27 different algorithms. The comparisons were structured under two case studies. The first concerns possible improvements in the performance of the forecasts in light of the use of sentiment analysis systems in time series forecasting. The second, having as a framework all the possible versions of the above configuration, concerns the selection of the methods that perform best. The results, as presented by various illustrations, indicate, on the one hand, the conditional improvement of predictability after the use of specific sentiment setups in long-term forecasts and, on the other, a universal predominance of long short-term memory architectures. |
| first_indexed | 2024-03-10T04:10:59Z |
| format | Article |
| id | doaj.art-43fb8ebb7ffb478bbbaa09ffd08a77e2 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T04:10:59Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-43fb8ebb7ffb478bbbaa09ffd08a77e22023-11-23T08:10:30ZengMDPI AGEntropy1099-43002021-11-012312160310.3390/e23121603A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series ForecastingCharalampos M. Liapis0Aikaterini Karanikola1Sotiris Kotsiantis2Department of Mathematics, University of Patras, 26504 Patras, GreeceDepartment of Mathematics, University of Patras, 26504 Patras, GreeceDepartment of Mathematics, University of Patras, 26504 Patras, GreeceIn practice, time series forecasting involves the creation of models that generalize data from past values and produce future predictions. Moreover, regarding financial time series forecasting, it can be assumed that the procedure involves phenomena partly shaped by the social environment. Thus, the present work is concerned with the study of the use of sentiment analysis methods in data extracted from social networks and their utilization in multivariate prediction architectures that involve financial data. Through an extensive experimental process, 22 different input setups using such extracted information were tested, over a total of 16 different datasets, under the schemes of 27 different algorithms. The comparisons were structured under two case studies. The first concerns possible improvements in the performance of the forecasts in light of the use of sentiment analysis systems in time series forecasting. The second, having as a framework all the possible versions of the above configuration, concerns the selection of the methods that perform best. The results, as presented by various illustrations, indicate, on the one hand, the conditional improvement of predictability after the use of specific sentiment setups in long-term forecasts and, on the other, a universal predominance of long short-term memory architectures.https://www.mdpi.com/1099-4300/23/12/1603time series forecastingmachine learningfinancial time seriessentiment analysisFinBERTmultivariate |
| spellingShingle | Charalampos M. Liapis Aikaterini Karanikola Sotiris Kotsiantis A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series Forecasting Entropy time series forecasting machine learning financial time series sentiment analysis FinBERT multivariate |
| title | A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series Forecasting |
| title_full | A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series Forecasting |
| title_fullStr | A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series Forecasting |
| title_full_unstemmed | A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series Forecasting |
| title_short | A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series Forecasting |
| title_sort | multi method survey on the use of sentiment analysis in multivariate financial time series forecasting |
| topic | time series forecasting machine learning financial time series sentiment analysis FinBERT multivariate |
| url | https://www.mdpi.com/1099-4300/23/12/1603 |
| work_keys_str_mv | AT charalamposmliapis amultimethodsurveyontheuseofsentimentanalysisinmultivariatefinancialtimeseriesforecasting AT aikaterinikaranikola amultimethodsurveyontheuseofsentimentanalysisinmultivariatefinancialtimeseriesforecasting AT sotiriskotsiantis amultimethodsurveyontheuseofsentimentanalysisinmultivariatefinancialtimeseriesforecasting AT charalamposmliapis multimethodsurveyontheuseofsentimentanalysisinmultivariatefinancialtimeseriesforecasting AT aikaterinikaranikola multimethodsurveyontheuseofsentimentanalysisinmultivariatefinancialtimeseriesforecasting AT sotiriskotsiantis multimethodsurveyontheuseofsentimentanalysisinmultivariatefinancialtimeseriesforecasting |