In this notebook, we implement a recurrent neural network to analyze how travelers in February 2015 expressed their feelings on Twitter. Using an RNN rather than a strictly feedforward network is more accurate since we can include information about the sequence of words.
A sentiment analysis job about the problems of each major U.S. airline. Twitter data was scraped from February of 2015 and contributors were asked to first classify positive, negative, and neutral tweets, followed by categorizing negative reasons (such as "late flight" or "rude service").
The dataset can be downloaded here.
In this notebook, our goal is to identify whether a tweet is negative or non-negative (positive or neutral).
This project is inspired by one of the mini-projects in the Udacity Deep Learning Nanodegree.