Sentiment-Driven Exchange Rate Forecasting: Integrating Twitter Analysis with Economic Indicators

Abstract

This study focuses on predicting the USD/TL exchange rate by integrating sentiment analysis from Twitter with traditional economic indicators. With the dynamic nature of global finance, accurate exchange rate forecasting is crucial for financial planning and risk management. While economic indicators have traditionally been used for this purpose, the increasing influence of public sentiment, particularly on digital platforms like Twitter, has prompted the exploration of sentiment analysis as a complementary tool. Our research aims to evaluate the effectiveness of combining sentiment analysis with economic indicators in predicting the USD/TL exchange rate. We employ machine learning techniques, including LSTM Neural Network, xgboost, and RNN, to analyze Twitter data containing keywords related to the Turkish economy alongside TL/USD exchange rate data. Our findings demonstrate that integrating sentiment analysis from Twitter enhances the predictive accuracy of exchange rate movements. This study contributes to the evolving landscape of financial forecasting by highlighting the significance of sentiment analysis in exchange rate prediction and providing insights into its potential applications in financial decision-making processes. JEL classification numbers: C53, F31, E60. Keywords: Twitter narratives, LSTM, XGBoost, RNN, USD/TL FX rate, Narrative economics.