Abstract—In this work, a software application was developed to analyze and visualize messages over
Twitter social network, ranking the posts relatively to variations in moods within the Brazilian territory. Artificial intelligence techniques such as text mining and sentiment analysis were used for this purpose. The use of methods of machine learning allows determining the polarity (positive or negative) of tweets collected. Results were displayed in cartograms, through representations of
tweet's geographic locations. Surprisingly, another study of
twitter’s mood from United States Nation showed similar results for the variation of moods throughout the day, hypothesizing a humor pattern for human beings during the period of 24 hours.
Index Terms—Twitter, sentiment analysis, social data mining.
David N. Prata, Kleber P. Soares, Michel A. Silva, Daniela Q. Trevisan, and Patrick Letouze are with the Department of Computer Science of the Federal University of Tocantins – “Universidade Federal do Tocantins”, Palmas-TO, 77.001-009 Brazil (e-mail: ddnprata@uft.edu.br).
[PDF]
Cite: David N. Prata, Kleber P. Soares, Michel A. Silva, Daniela Q. Trevisan, and Patrick Letouze, " Social Data Analysis of Brazilian’s Mood from Twitter," International Journal of Social Science and Humanity vol. 6, no. 3, pp. 179-183, 2016.