Monday, 16 Apr 2018
NLTK is a powerful library that allows you to work with human language data. With it you can process text for classification, tokenization, stemming, tagging and parsing. Since I was taking the Datacamp course - Natural Language Processing Fundamentals in Python and was learning about NLTK I decided to use this library to create a Tweet classification script to be used on a term.
One of the Pybites challenges was to create a Twitter sentiment analysis in order to get a ratting about a subject. After the analysis is done the searched term would get a rating for Good, Bad, Neutral.
Pybites solution uses the textblob library, but since I was learning about NLTK at the time I have decided to use this library and implement my own version of a classifier. Working on this exercise was extremely fun and made me learn a lot.
GitHub repo: https://github.com/FabioRosado/tweetnalytic
Pybites challenge 07: https://pybit.es/codechallenge07.html
Image credits: Unsplash