Sentiment Analysis

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.

Background: Recent advancements in Natural Language Processing (NLP) have been significantly influenced by transformer models. However, challenges related to scalability, discrepancies between pretraining and finetuning, and suboptimal performance on tasks with diverse and limited data remain. The integration of Reinforcement Learning (RL) with transformers has emerged as a promising approach to address these limitations. Objective: This article aims to evaluate the performance of a transformer-based NLP model integrated with RL across multiple tasks, including translation, sentiment analysis, and text summarization. Additionally, the study seeks to assess the model's efficiency in real-time operations and its fairness. Methods: The hybrid model's effectiveness was evaluated using task-oriented metrics such as BLEU, F1, and ROUGE scores across various task difficulties, dataset sizes, and demographic samples. Fairness was measured based on demographic parity and equalized odds. Scalability and real-time performance were assessed using accuracy and latency metrics. Results: The hybrid model consistently outperformed the baseline transformer across all evaluated tasks, demonstrating higher accuracy, lower error rates, and improved fairness. It also exhibited robust scalability and significant reductions in latency, enhancing its suitability for real-time applications. Conclusion: This article illustrates that the proposed hybrid model effectively addresses issues related to scale, diversity, and fairness in NLP. Its flexibility and efficacy make it a valuable tool for a wide range of linguistic and practical applications. Future research should focus on improving time complexity and exploring the use of deep unsupervised learning for low-resource languages.

This study investigates the way in which public discourse on social media reflects and shapes global power dynamics surrounding AI. Leveraging a corpus of approximately 21,000 English-language posts from Platform X (2021–2025), this study utilizes a computational linguistics framework—incorporating topic modeling, sentiment analysis, emotion classification, and named entity recognition—to analyze the construction of AI, interrogating its thematic narratives and affective investments across geopolitical contexts. Findings reveal a discourse shaped by U.S.–China technological rivalry, AI militarization, and infrastructural sovereignty, with strong currents of fear, anger, and skepticism. While Western powers and corporate actors dominate the narrative space, alternative discourses from the Global South emphasize digital dependency, exclusion, and justice. The emotional intensity and thematic complexity of the discourse suggest that publics are not simply reacting to geopolitical developments, but actively construct contested imaginaries of AI’s role in world order. This research contributes to a growing body of literature that recognizes public discourse as a critical site of informal geopolitics and underscores the need for more inclusive, responsive, and ethically grounded AI governance frameworks.