News for hackers. Stuff that matters.
Re:Daily happiness averages using Twitter by taoufix on Tuesday May 07, 2013 @04:39AM (#5667072)
I wonder how do they deal with negative phrases:

* not happy

* far from being happy

* I could use some happy moments

* ... etc

Re:Daily happiness averages using Twitter by achal on Tuesday May 07, 2013 @05:32AM (#5667209)
As far as I can tell, they currently don't.

  “How will you deal with context?”

  We are currently developing a principled method to identify 
  relevant phrases, for example to deal with the multitude of both 
  positive and negative uses of profanity. We expect to be scoring 
  phrases instead of words, where appropriate, in the near 
  future."
Also, they mention elsewhere that they use a bag of words classifier, so they can't really account for things like this easily.
Re:Daily happiness averages using Twitter by program on Tuesday May 07, 2013 @05:32AM (#5667206)
I wonder how they deal with ironic statements. It seems that they merely extract words out of the context.
Re:Daily happiness averages using Twitter by lucb1e on Tuesday May 07, 2013 @07:53AM (#5667598)
How do you deal with ironic statements, program? ;)
Re:Daily happiness averages using Twitter by hammock on Tuesday May 07, 2013 @12:21PM (#5668934)
They don't. But consider that a good bit of those would be neutralized by phrases like "not sad" etc.