Automated Deep/Machine Learning for NLP: Text Prediction

This article starts by discussing the fundamentals of Natural Language Processing (NLP) and later demonstrates using Automated Machine Learning (AutoML) to build models to predict the sentiment of text data. Other applications of NLP are for translation, speech recognition, chatbot, etc. You may be thinking that this article is general because there are many NLP tutorials and sentiment analyses on the internet. But, this article tries to show something different. It will demonstrate the use of AutoKeras as an AutoML to generate Deep Learning to predict text, especially sentiment rating and emotion. But before that, let's briefly discuss basic NLP because it supports text sentiment prediction. NLP aims to make the sense of text data. The examples of text data commonly analyzed in Data Science are reviews of products, posts from social media, documents, etc. Unlike numerical data, text data cannot be analyzed with descriptive statistics. If we have a list of product prices data containing 1000 numbers, we can understand the overall prices data by examining the average, median, standard deviation, boxplot, and other technics. We do not have to read all the numbers to understand them.