Sentiment Analysis using NLP

 In this article, I am going to tell you that I have made a sentiment analysis using unsupervised lexicon-based models first one is AFINN Lexicon,sentiwordnet lexicon, and another one Vader lexicon.

The AFINN LEXION  is perhaps one of the simplest and most popular lexicons that can be used extensively for sentiment analysis. The current version of the lexicon is AFINN-en-165. txt, and it contains over 3,300+ words with a polarity score associated with each word. You can find this lexicon at the author’s official GitHub repository.

SENTIWORDNET LEXION: SENTIWORDNET is the result of the automatic annotation of all the synsets of WORDNET according to the notions of “positivity”, “negativity”, and “neutrality”. 

here AFINN accuracy is 71.18 % and f1 score is 74.68

In the above picture, you can see Sentinetword  accuracy is 68.43 %, and f1 score 70.27%

as you can see Vader accuracy  is 71.07 % and f1 score is 74.21 

so my conclusion is that AIFNN is the best 

Sentiment Analysis using supervised learning 

I got an Accuracy 89.73 precision 88.56 recall 91.29 and f1 score by using supervised machine learning as compared to AFINN accuracy is 71.18 % and f1 score is 74.68. So supervised learning is better