[ripb]

>It's just not accurate enough on 140 character tweets.

I would disagree but apply the caveat that there has to be heavy filtering of what is being analysed to derive anything of value from it.

A tweet like:

"“@BarkhamTaylor: #beatcameronathisowngame @aliceehoughton” let's get it trending #adrian"

Has no value for sentiment analysis, yet is lumped in with the rest of them, while something like:

"Sunny day in London :) @ Green Park http://t.co/S71RQR2luU"

Clearly has value regarding sentiment analysis. The current problem being that all of the junk gets marked as "average" or similar because sentiment can't be derived from it, which in the overall set skews things greatly.