This study investigates the role of sentiment analysis in improving exchange rate prediction models, providing empirical evidence for narrative economics; the idea that economic outcomes are shaped by prevailing beliefs and popular narratives. By integrating sentiment-based features into predictive frameworks, we demonstrate that exchange rate movements are influenced by subjective factors beyond traditional economic variables. Our findings suggest that market sentiment systematically impacts currency fluctuations. To assess the effectiveness of sentiment-enhanced models, we compare various forecasting approaches. Notably, a generalized linear model (GLM) outperforms more complex deep learning architectures, including long short-term memory (LSTM) networks and hybrid CNN-LSTM models. Additionally, even an optimized multilayer perceptron (MLP) fails to surpass GLM performance, highlighting the potential linearity of the relationship between predictors and exchange rates. These results underscore the importance of aligning model complexity with the statistical properties of the target variable. Beyond exchange rate forecasting, our study underscores the broader significance of incorporating sentiment and narratives into economic models. By acknowledging the role of subjective beliefs, researchers and policymakers can enhance predictive accuracy and improve decision-making processes in financial markets.