The first part of the course I have been taking on data science deals with analysis of Twitter data. This is aimed at discerning the overall sentiment of a Tweet or collection of tweets.
To get this going the first thing you need is a big collection of tweets in a format that is easy for a program to digest. Step in JSON, a text based output that represents data in a collection of arrays. Once you have this data set you can then start experimenting. Maybe try something simple first, like taking ten minutes worth of samples every hour and mapping the twitter activity for an average of how many tweets per country for that hour.
I’ll be putting up one or two examples of what you can do with this data in the coming days and weeks.
This post has been viewed 1309 times.