Volume 2 - Issue 2, March - April 2026

Financial sentiment analysis has emerged as a crucial research area due to the growing influence of textual data on financial decision-making processes. With the rapid expansion of online financial news, social media platforms, analyst reports, and corporate disclosures, Natural Language Processing (NLP) techniques play a significant role in extracting sentiment-driven insights from unstructured financial text. This survey presents a comprehensive overview of existing approaches used in financial sentiment analysis, highlighting traditional methods, machine learning models, and recent deep learning-based techniques. The paper discusses commonly used datasets, domain-specific sentiment lexicons, and evaluation metrics employed in financial contexts. Furthermore, it analyzes the challenges unique to financial language, such as domain ambiguity, sarcasm, temporal relevance, and data imbalance. Recent advancements involving transformer-based models and hybrid approaches are also examined to understand their impact on prediction accuracy and robustness. Finally, the survey outlines open research issues and future directions, emphasizing the need for explainable models and real-time sentiment analysis systems for practical financial applications. This work aims to provide researchers and practitioners with a structured understanding of the current state and potential growth of financial sentiment analysis using NLP.

Ms.S.Abinaya, Ms.D.Mariyam Beevi,"A Survey on Financial Sentiment Analysis Using Natural Language Processing" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(2): Page(762-772) Mar-Apr 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.