hello you described in your nltk tutorial that how naive bayes algorithms apply when words as a features but my question is when we take sentiwordnet as a feature in that case the output is csv file where every features in some floting value so how can we train and test them?
You must be logged in to post. Please login or register an account.
You assign a unique value to each word, both with the sentiment words and the words in your testing data. That's generally why you do stemming or lemmatizing as well.
-Harrison 9 years ago
You must be logged in to post. Please login or register an account.
That's not my question i can better explain with screenshot but here is not possible so i ll sent you full description with screenshot in your this Contact: Harrison@pythonprogramming.net. email id. is it ok ?
-Rachana 9 years ago
You must be logged in to post. Please login or register an account.