Hey Randerson, thanks for the post. Do you see any strategies to avoid having a model that misclassifies positive tweets? For example, on your list of negative tweets the first three are great examples of positive tweets that just had negative words because they were about complicated issues. With the exception of the first that was just "Game on". Any tips on how to get the model to be more nuanced? Thanks for the great post! Cheers

Written by

AI engineer at K1 Digital and co-organizer of the Deep Learning Sessions meet up in Lisbon. AI |Computer Vision| Data Science| Productivity | Learning

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store