App

Collection of lightweight data applications

Sentiment Classifier

Write a movie review! Click outside the box to generate the sentiment.

How it works

This notebook contains this pipeline from preprocessing movie reviews to building a sentiment classifier model. It classifies 88% validation reviews correctly - but does not do equally well on short reviews.

The texts are first represented by 10k TFIDF word scores that represent word affinity. These features are then feeded in a standard dense neural network, with 6 layers and gradually fewer neurons. Finally, the network outputs a single chance for being a positive review, between 0 and 1.