01. Intro
Sentiment Prediction RNN
Welcome to this lesson on building a recurrent neural network for predicting sentiment. This is intended to give you more experience building RNNs. I'm using the dataset from Luis's Mini-Project in the Deep Learning Section, a bunch of movie reviews from IMDB labeled with sentiment (positive or negative). But this time, you'll be using RNNs to get better results!
I'm going to have you implement this RNN. You can find the notebooks in our public GitHub repo. You can download the notebooks from the sentiment-rnn
folder there, or clone the repository:
git clone https://github.com/udacity/deep-learning.git
If you already have the repo, do a git pull
to get the new notebooks.
The Data
The data, reviews.txt
and labels.txt
, is located in the sentiment_network
directory. You can also find the labels here and the reviews here.