Market Prediction in Criptocurrency: A Systematic Literature Mapping

  • André Henrique de Oliveira Monteiro Universidade Federal de Itajubá
  • Adler Diniz de Souza Universidade Federal de Itajubá
  • Bruno Guazzelli Batista Universidade Federal de Itajubá
  • Mauricio Zaparoli Universidade Federal de Itajubá


The social media exerts an important role in publishing information and newspaper online. The quality of this information and the sentiment analysis might help predict the price of diverse market asset and cause great gains and losses. In this scenario, many researchers have been studying the diverse aspects that influence this area. Recently, cryptocurrencies have gained a spotlight between financial assets and, one of its characteristics is the fact that its market is strongly influenced by opinions and speculation being a proper area for sentiment analysis and data mining techniques. However, there is not any complete theoretical and technical framework about this subject. Due to its interdisciplinary characteristics involving topics in economics, human behavior, and artificial intelligence, there is a lack of clarity about the techniques and tools used in sentiment analysis in the cryptocurrencies scenario. The goal of this paper is to analyze related research in market prediction based on text mining and other artificial intelligence techniques and generate a systematic mapping about the main research, identifing the possible gaps in this field. This work might help the research community to better structure this emerging area and identify more exactly aspects that require research and are of essential importance.
Palavras-chave: Text Mining, Prediction algorithms, Criptocurrency, Markets, Artificial intelligence
MONTEIRO, André Henrique de Oliveira; DE SOUZA, Adler Diniz; BATISTA, Bruno Guazzelli; ZAPAROLI, Mauricio. Market Prediction in Criptocurrency: A Systematic Literature Mapping. In: SIMPÓSIO BRASILEIRO DE SISTEMAS DE INFORMAÇÃO (SBSI), 15. , 2019, Aracajú. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2019 . p. 487-494.