An integrated bibliometric and content analysis of financial natural language processing: advancements and challenges

Financial natural language processing (NLP) is increasingly essential for analysing unstructured financial text to support improved decision-making. While prior studies identified key applications, but lacked a comprehensive analysis of influential works, trends and guiding theories, a gap this study addresses. Using bibliometric and content analysis, this research examines 684 Financial NLP articles from WoS (1999-2025) to map publication trends, influential authors, collaborations, and themes. An in-depth analysis of 105 high-impact studies is conducted to identify dominant methodologies, applications, and theories. The findings reveal a significant rise in Financial NLP research after 2020, with an annual growth rate of 4.32%, highlighting major applications such as sentiment analysis, risk assessment, fraud detection, and algorithmic trading. While deep learning models remain dominant, emerging frontiers include explainable artificial intelligence, large language models, and real-time financial analytics. This study provides insights for academics, policymakers, and practitioners, laying a foundation for future research.