CISTI'2014 - 9ª Conferencia Ibérica de Sistemas y Tecnologías de Información

Full Program »

¿QUE TIPOS DE SENTIMIENTOS SON EXPRESADOS EN TWEETS DE USUARIOS CON BUENA REPUTACIÓN EN EL CAMPO DE LA SALUD?

One of the important types of information on the Web is the opinions expressed in the user generated content, posted on Twitter, Facebook and others social networks. Sentiment analysis and opinion mining is the field of study that analyzes people’s opinions, sentiments, evaluations, attitudes, and etc. Recently, it has attracted great interest both in academia and in industry due to its useful potential applications. In this paper we evaluated a set of tweets from a timeline of Twitter users. We analyzed the dataset based on two different approaches: lexical analysis and syntactic analysis. We also perform a comparative study to find out if there is a correlation between user reputation and user sentiment. The experimental finding with both approaches shown similar results, which means, that does not make difference between stopword removal or not. Further, the paper exemplifies the applications of this research and its limitations.

Author(s):

Leila Weitzel    
Universidade Federal do sul e Sudeste do Pará
Brazil

Raul Freire Aguir    
Universidade Federal do Sul e Sudeste do Pará
Brazil

Walter Fernando García Rodriguez    
Universidade Federal do Sul e Sudeste do Pará
Brazil

Marcela Gomes Heringer    
Universidade Federal do Sul e Sudeste do Pará
Brazil

 

Powered by OpenConf®
Copyright ©2002-2013 Zakon Group LLC