Keras Deep Learning Cookbook

Getting ready

Let's load the dataset and calculate some of its properties. We will start off by loading the sentiment dataset and extracting text and the corresponding sentiment label. We will be keeping only the necessary columns.

About this dataset

This data originally came from Crowdflower's data for everyone library (https://www.figure-eight.com/data-for-everyone/).

As the original source says, we looked through tens of thousands of tweets about the early August Grand Old Party (GOP) debate in Ohio and asked contributors to do both sentiment analysis and data categorization. Contributors were asked if the tweet was relevant, which candidate was mentioned, what subject was mentioned, and then what the sentiment was for a given tweet. ...