That's how looked the evolution of the mood in different regions of the world from August to October 2014:
- daily text retrieval from news websites,
- analysis of the html with regular expressions,
- calculation of a mood score by comparison of the treated text with the word list afinn ,
- storage in a database using MySQLdb,
- dealing with the data with Pandas,
- plot the results interactively with Bokeh.
All the code is available at GitHub.
Visit TheMoodOfTheWorld.weebly.com for more plots.