Investigation of the relationship between number of tweets and USDTRY exchange rate with wavelet coherence and transfer entropy analysis
Abstract Predicting the currency exchange rate is crucial for financial agents, risk managers, and policymakers. Traditional approaches use publicly announced news on macroeconomic and financial variables as predictors of currency exchange. However, the rise of social media may have changed the sour...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Financial Innovation |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40854-024-00710-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841544379392589824 |
|---|---|
| author | Cengiz Karatas Sukriye Tuysuz Kazim Berk Kucuklerli Veysel Ulusoy |
| author_facet | Cengiz Karatas Sukriye Tuysuz Kazim Berk Kucuklerli Veysel Ulusoy |
| author_sort | Cengiz Karatas |
| collection | DOAJ |
| description | Abstract Predicting the currency exchange rate is crucial for financial agents, risk managers, and policymakers. Traditional approaches use publicly announced news on macroeconomic and financial variables as predictors of currency exchange. However, the rise of social media may have changed the source of information. For instance, tweets can help investors make informed decisions about the foreign exchange (FX) market by reflecting market sentiment and opinion. From another aspect, changes in currency exchange may incite agents to post tweets. Are tweets good predictors of currency exchange? Is the relationship between tweets and currency exchange bidirectional? We investigate the comovement/causality between the number of #dolar (“enflasyon” resp.) tweets and USDTRY currency exchange using wavelet coherence and transfer entropy (TE) to answer these questions. Wavelet coherence allows us to determine the relationship between the number of tweets and the USDTRY rate by considering the time–frequency domain. TE enables us to quantify the net information flow between the number of tweets and USDTRY. Data from October 2020 to March 2022 were used. The obtained results remain robust regardless of the frequency of retained data (daily or hourly) and the methods used (wavelet or TE). Based on our results, USDTRY is correlated with the number of #dolar tweets (#inflation) mainly in the short run and a few times in the medium run. These relationships change through time and frequency (wavelet analysis results). However, the results from TE indicate a bidirectional relationship between the #dolar (#inflation) tweets number and the USDTRY exchange rate. The influence of the exchange rate on the number of tweets is highly pronounced. Financial agents, risk managers, policymakers, and investors should then pay moderate attention to the number of #dolar (#inflation) tweets in trading/forecasting the USD–TRY exchange rate. |
| format | Article |
| id | doaj-art-b07a1e26c3744f60a3fc84e4876fadc4 |
| institution | Kabale University |
| issn | 2199-4730 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Financial Innovation |
| spelling | doaj-art-b07a1e26c3744f60a3fc84e4876fadc42025-01-12T12:36:18ZengSpringerOpenFinancial Innovation2199-47302025-01-0111112010.1186/s40854-024-00710-7Investigation of the relationship between number of tweets and USDTRY exchange rate with wavelet coherence and transfer entropy analysisCengiz Karatas0Sukriye Tuysuz1Kazim Berk Kucuklerli2Veysel Ulusoy3Faculty of Business Administration, Haliç UniversityInternational Finance Department, Yeditepe UniversityFinancial Risk Management, PwCDepartment of Economics, Morrissey College of Arts and Sciences, Boston CollegeAbstract Predicting the currency exchange rate is crucial for financial agents, risk managers, and policymakers. Traditional approaches use publicly announced news on macroeconomic and financial variables as predictors of currency exchange. However, the rise of social media may have changed the source of information. For instance, tweets can help investors make informed decisions about the foreign exchange (FX) market by reflecting market sentiment and opinion. From another aspect, changes in currency exchange may incite agents to post tweets. Are tweets good predictors of currency exchange? Is the relationship between tweets and currency exchange bidirectional? We investigate the comovement/causality between the number of #dolar (“enflasyon” resp.) tweets and USDTRY currency exchange using wavelet coherence and transfer entropy (TE) to answer these questions. Wavelet coherence allows us to determine the relationship between the number of tweets and the USDTRY rate by considering the time–frequency domain. TE enables us to quantify the net information flow between the number of tweets and USDTRY. Data from October 2020 to March 2022 were used. The obtained results remain robust regardless of the frequency of retained data (daily or hourly) and the methods used (wavelet or TE). Based on our results, USDTRY is correlated with the number of #dolar tweets (#inflation) mainly in the short run and a few times in the medium run. These relationships change through time and frequency (wavelet analysis results). However, the results from TE indicate a bidirectional relationship between the #dolar (#inflation) tweets number and the USDTRY exchange rate. The influence of the exchange rate on the number of tweets is highly pronounced. Financial agents, risk managers, policymakers, and investors should then pay moderate attention to the number of #dolar (#inflation) tweets in trading/forecasting the USD–TRY exchange rate.https://doi.org/10.1186/s40854-024-00710-7TweetsTweets numberCurrency exchangeWavelet coherenceTransfer entropy |
| spellingShingle | Cengiz Karatas Sukriye Tuysuz Kazim Berk Kucuklerli Veysel Ulusoy Investigation of the relationship between number of tweets and USDTRY exchange rate with wavelet coherence and transfer entropy analysis Financial Innovation Tweets Tweets number Currency exchange Wavelet coherence Transfer entropy |
| title | Investigation of the relationship between number of tweets and USDTRY exchange rate with wavelet coherence and transfer entropy analysis |
| title_full | Investigation of the relationship between number of tweets and USDTRY exchange rate with wavelet coherence and transfer entropy analysis |
| title_fullStr | Investigation of the relationship between number of tweets and USDTRY exchange rate with wavelet coherence and transfer entropy analysis |
| title_full_unstemmed | Investigation of the relationship between number of tweets and USDTRY exchange rate with wavelet coherence and transfer entropy analysis |
| title_short | Investigation of the relationship between number of tweets and USDTRY exchange rate with wavelet coherence and transfer entropy analysis |
| title_sort | investigation of the relationship between number of tweets and usdtry exchange rate with wavelet coherence and transfer entropy analysis |
| topic | Tweets Tweets number Currency exchange Wavelet coherence Transfer entropy |
| url | https://doi.org/10.1186/s40854-024-00710-7 |
| work_keys_str_mv | AT cengizkaratas investigationoftherelationshipbetweennumberoftweetsandusdtryexchangeratewithwaveletcoherenceandtransferentropyanalysis AT sukriyetuysuz investigationoftherelationshipbetweennumberoftweetsandusdtryexchangeratewithwaveletcoherenceandtransferentropyanalysis AT kazimberkkucuklerli investigationoftherelationshipbetweennumberoftweetsandusdtryexchangeratewithwaveletcoherenceandtransferentropyanalysis AT veyselulusoy investigationoftherelationshipbetweennumberoftweetsandusdtryexchangeratewithwaveletcoherenceandtransferentropyanalysis |