Financial News
Financial news analysis aims to understand how news impacts financial markets, primarily focusing on predicting stock movements and investor sentiment. Current research heavily utilizes large language models (LLMs) and advanced architectures like geometric hypergraphs and attention networks to extract structured information, perform sentiment analysis at granular levels (e.g., per company), and improve the accuracy of stock trend prediction, even in few-shot learning scenarios. These advancements offer significant potential for improving investment strategies, risk management, and the overall efficiency of financial markets by providing more accurate and timely insights from the vast amount of unstructured financial news data.
Papers
Automatic detection of relevant information, predictions and forecasts in financial news through topic modelling with Latent Dirichlet Allocation
Silvia García-Méndez, Francisco de Arriba-Pérez, Ana Barros-Vila, Francisco J. González-Castaño, Enrique Costa-Montenegro
Detection of Temporality at Discourse Level on Financial News by Combining Natural Language Processing and Machine Learning
Silvia García-Méndez, Francisco de Arriba-Pérez, Ana Barros-Vila, Francisco J. González-Castaño