Multilevel exploration in Twitter social stream
Luigi Lancieri, Romain Giovanetti · 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · 2016
This paper describes a methodology approach and a tool dedicated to the exploration of the Twitter social stream by combining different contextual parameters such as time, keywords, gender or the opinion. The exploration can be made in two main modes depending on the fact that the phenomenon is either known or not. The first mode, similar to the use of Googlefight search engine, allows to compare the stream feedback for several groups of words. A typical example, that we will discuss, consists in evaluating trends in the domains of fashions or politic. The second mode consists in exploring the timeline of the social stream looking for unknown emerging events. This mode can be used to explore the past or to identify, in near real time, an event that will probably make the buzz.