I am keen on working with Mathematica for my sentimental analysis project. I have just started and been working around with some examples. During which I found:

In  := Classify["Sentiment", {"This movie is not at all bad"}]
Out := {Negative}

In  := Classify["Sentiment", {"This movie is not at all bad"},
Out := {<|"Positive" -> 0.252816, "Neutral" -> 0.0508273, 
  "Negative" -> 0.696357|>}

Which is not really the right answer. How do I overcome this?

  • 1
    $\begingroup$ related: mathematica.stackexchange.com/a/64317/27539. I don't think there is much you can do about this, except using some other language like python with its many provided machine learning libraries, which grants you greater customization and control of what is happening under the hood. $\endgroup$
    – glS
    Feb 10, 2017 at 9:27


Browse other questions tagged or ask your own question.