Evaluation of transformer models for financial targeted sentiment analysis in Spanish

Abstract

Nowadays, financial data from social media plays an important role to predict the stock market. However, the exponential growth of financial information and the different polarities of sentiment that other sectors or stakeholders may have on the same information has led to the need for new technologies that automatically collect and classify large volumes of information quickly and easily for each stakeholder. In this scenario, we conduct a targeted sentiment analysis that can automatically extract the main economic target from financial texts and obtain the polarity of a text towards such main economic target, other companies and society in general. To this end, we have compiled a novel corpus of financial tweets and news headlines in Spanish, constituting a valuable resource for the Spanish-focused research community. In addition, we have carried out a performance comparison of different Spanish-specific large language models, with MarIA and BETO achieving the best results. Our best result has an overall performance of 76.04%, 74.16%, and 68.07% in macro F1-score for the sentiment classification towards the main economic target, society, and other companies, respectively, and an accuracy of 69.74% for target detection. We have also evaluated the performance of multi-label classification models in this context and obtained a performance of 71.13%.