Sentiment Analysis


#1

I want to run some sentiment analysis using metapy toolkit. I am a little confuse on how use metapy for this, my initial thought was to load up all the documents in a line corpus and then run something like naive bayes to see if we can predict if the comments are positive or negative.

Any help will be appreciative.


#2

That sounds reasonable. You will need some labeled training data to do something like this, but you can certainly train a classifier for a binary classification task (positive vs. negative sentiment) for this.