An Approach to Sentiment Analysis of Web Applications in Portuguese

  • Renato F. Martins CEFET-MG
  • Fabrício Benevenuto UFMG
  • Adriano Pereira UFMG

Resumo


Sentiment analysis has been applied in many contexts, including user reviews analysis on products and services, trends and financial market moods. Established methods for sentiment analysis present a behavior that varies according to the application and its lexical base, generating different results among them. In this paper, a new sentiment analysis technique called SentiPipe will be presented, which takes the best of a set of methods, generating a less sensitive analysis based context. For such, it was used a real Web database of financial market news in Portuguese to which was applied the new sentiment detection proposal. The results were promising, showing improvement in al
Palavras-chave: Análise de Sentimentos, Redes Sociais, Classificação de Texto, Aplicações Web, Web 2.0, Língua Portuguesa
Publicado
27/10/2015
Como Citar

Selecione um Formato
MARTINS, Renato F.; BENEVENUTO, Fabrício; PEREIRA, Adriano. An Approach to Sentiment Analysis of Web Applications in Portuguese. In: SIMPÓSIO BRASILEIRO DE SISTEMAS MULTIMÍDIA E WEB (WEBMEDIA), 1. , 2015, Manaus. Anais do XXI Simpósio Brasileiro de Sistemas Multimídia e Web. Porto Alegre: Sociedade Brasileira de Computação, oct. 2015 . p. 105-112.

Artigos mais lidos do(s) mesmo(s) autor(es)