Analysing and visualizing tweets for U.S. president popularity

In our society we are continually invested by a stream of information (opinions, preferences, comments, etc.). This shows how Twitter users react to news or events that they attend or take part in real time and with interest. In this context it becomes essential to have the appropriate tools in order to be able to analyze and extract data and information hidden in their large number of tweets. Social networks are a source of information with no rivals in terms of amount and variety of information that can be extracted from them. We propose an approach to analyze, with the help of automated tools, comments and opinions taken from social media in a real time environment. We developed a software system in R based on the Bayesian approach for text categorization. We aim of identifying sentiments expressed by the tweets posted on the Twitter social platform. The analysis of sentiment spread on social networks allows to identify the free thoughts, expressed authentically. In particular, we analyze the sentiments related to U.S President popularity by also visualizing tweets on a map. This allows to make an additional analysis of the real time reactions of people by associating the reaction of the single person who posted the tweet to his real time position in Unites States. In particular, we provide a visualization based on the geographical analysis of the sentiments of the users who posted the tweets.