Calculate sentiment from multiple languages

[dkocich]

I translated AFINN 165 to other languages and now it is possible to get sentiment value from various texts. I tried to evaluate my fork using the connection to the Twitter stream (+/- 40 languages in a few million of messages) and it worked quite fine and it is sufficient to my current requirements (to be fast for streaming and evaluate many languages using one tool). There is a place for optimization of some problems of course but I think that it can be handled in new versions later and this one can serve to others also.
Do you have some comments? Should I add something more? Thanks for this tool, review and have a nice day.

[thisandagain]

This is really neat! It would be wonderful to extend this beyond English.

We'll need to establish a set of labeled sentences (see #103 as well as the original AFINN paper) in order be able to determine the accuracy of these translations. While Google Translate is great, sentiment can be pretty subtle and so I wonder if something like Pootle or Transifex might be able to help us source translations of the AFINN word list with greater confidence.

I've been thinking about ways to fund a CrowdFlower campaign to handle establishing labeled corpora for different languages. I don't think it would take much (maybe $60 - $120 USD) per language to get things started. Until we have some of this sorted out I am going to close this but open up an issue for tracking. Thanks!