The Twitter platform has gained millions of users from all around the world and it is generating an endless stream of data. Although Twitter is also used routinely by PR departments of corporations, universities, and heads of states to propagate their agendas to public, the majority of tweets still comes from regular users and can possibly be utilized as a probe of a "public mood" on a variety of subjects.
A simple Shiny application allows one to perform basic text mining operations on a sample of relatively new tweets coming from various places. Below I'll give you an insight on how to use this application. If you are not familiar with the Text Frequency - Inverse Document Frequency (TF-IDF) method, think of it as a reweighting technique that allows one to rank down "low information" words like "the", "and", or "have" and rank up infrequent, possibly informative words.
Unfortunately I do not have a shiny server on my own. The application data is updated every time you open the link above, which results in a noticeable delay. Please, bear with a half-minute delay.
