This article presents a comparative study of large language models (LLMs) in the task of sentiment analysis of financial market news. This work aims to analyze the performance difference of these models in this important natural language processing task within the context of finance. LLM models are compared with classical approaches, allowing for the quantification of the benefits of each tested model or approach. Results show that large language models outperform classical models in the vast majority of cases.
Paper
References (15)
10Random forest na an ´ alise de sentimentos em jogos digitais2024 · Reposit ´ orio Institucional SENAI CIMATEC . Artigo de Especializac¸˜ao em Data Science & Analytics
11Explorando a e fi c´acia das linguagens generativas em tarefas de an´alise de sentimentos no portuguˆes brasileiro2024 · Linguam´atica
12Avaliac¸˜ao de desempenho dos modelos de aprendizado de m´aquina para previs˜ao de prec¸os de ac¸˜oes do mercado fi nanceiro2024 · European Journal of Technology
Scroll for more · 3 remaining