Deep Learning para BigData

• Autor(a) principal: Correia, Filipe José Ribeiro
• Data de Publicação: 2021
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10400.22/19365
• topic: Deep Learning; Big Data; Neural Network; Stock Data; Financial Markets; Social Networks; Redes Neuronais; Dados de ações; Mercados Financeiros; Redes Sociais

We live in a world where data is becoming increasingly valuable and increasingly abundant in volume. Every company produces data, be it from sales, sensors, and various other sources. Since the dawn of the smartphone, virtually every person in the world is connected to the internet and contributes to data generation. Social networks are big contributors to this Big Data boom. How do we extract insight from such a rich data environment? Is Deep Learning capable of circumventing Big Data’s challenges? This is what we intend to understand. To reach a conclusion, Social Network data is used as a case study for predicting sentiment changes in the Stock Market. The objective of this dissertation is to develop a computational study and analyse its performance. The outputs will contribute to understand Deep Learning’s usage with Big Data and how it acts in Sentiment analysis.