Sentiment Analysis in Financial Data

• Grant number: 24/17511-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: February 01, 2025
• End date: December 31, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Lilian Berton
• Grantee: João Victor Assaoka Ribeiro
• Host Institution: Instituto de Ciência e Tecnologia (ICT). Universidade Federal de São Paulo (UNIFESP). Campus São José dos Campos. São José dos Campos , SP, Brazil

Abstract

In the financial market, the speed and impact of information such as news, social media posts and press releases play a crucial role in the decision-making of investors, companies and governments. Events such as interest rate changes, earnings reports or political and economic developments generate rapid reactions that result in price fluctuations of financial assets. The growing influence of social media also amplifies this effect. With the increasing volume of information and the limited human capacity to process it, sentiment analysis becomes an essential tool. Sentiment analysis is a natural language processing (NLP) technique that identifies and classifies opinions expressed in texts, assessing whether they are positive, negative or neutral. This technique is already widely applied in several fields, including monitoring consumer reactions and analyzing social networks. This project aims to develop NLP and machine learning models to classify emotions in financial news in Portuguese. To this end, a dataset specialized in financial news will be created and state-of-the-art models, such as BERTimbau, Llama, Gemini and GPT, will be tested in order to compare their effectiveness in the different approaches. The results will contribute to the advancement of sentiment analysis in Portuguese, providing a valuable tool for interpreting emotions in financial texts and their impact on markets.