I wanted to perform Twitter sentiment analysis on Twitter tweets. When I googled it, I found a [stanfordNLP][1] code of sentiment class. I used it for finding Twitter sentiment later I came to know [twitter Gate][2] model is made for Twitter tweets only. 

Then I replaced the stanfordNLP model with TwitterGate model. I did not find any difference in the sentiment results. Both models give the same result. But when I tested same tweets with monkeylearn api and datumbox api sentiment results. I got confused. In NLP and twitterGate most tweets sentiment is given as negative where same Tweets sentiment is given as neutral in **Monkeylearn** & **Datumbox apis** code. 

How can I know model which is giving the correct sentiment? 


  [1]: http://nlp.stanford.edu/
  [2]: https://gate.ac.uk/wiki/twitter-postagger.html