What I meant by data cleaning is that

  • Removing Punctuations
  • Lower Casing
  • Removing Stop words
  • Removing irrelevant symbols, links and emojis

According to my knowledge, things like Punctuations, Capital Letters, Stop words like 'But' and emojis and such tend to intensifies the VADER sentiment value, or in other words it affects the sentiment.

So should I clean my data or leave punctuations, capital letters and stop words since VADER makes use of them as well?


1 Answer 1


DO NOT CLEAN, ALL CAPS AND PUNCTUATION MEAN SOMETHING!!!!! Let the model decide what the irrelevant symbols and emojis are, otherwise you could be getting rid of a useful sentiment signal ¯_(ツ)_/¯

  • 1
    $\begingroup$ Does this apply to url links as well? Will VADER ignore url links if they are in a text? $\endgroup$ Feb 12, 2022 at 7:53
  • $\begingroup$ I don't know if VADER will ignore URL's, but I filter them out of tweets when using VADER. $\endgroup$
    – ViennaMike
    Feb 3 at 4:09

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.