Text analytics is also often called text mining. This is basically the process of extracting and deriving meaningful patterns from textual data which can in turn be translated into actionable knowledge and insights. Text analytics consist of a collection of machine learning, natural language processing, linguistic, and statistical methods that can be leveraged to analyze text data. Machine-learning algorithms are built to work on numeric data in general, so extra processing and feature extraction and engineering is needed for text analytics to make regular machine learning and statistical methods work on unstructured data.

Natural language processing, popularly known as NLP, aids in doing this. NLP is defined as a specialized field in computer science and engineering and artificial intelligence which has its roots and origins in computational linguistics. Concepts and techniques from NLP are extremely useful and help in building applications and systems that enable interaction between machines and humans with the aid of natural language which is indeed a daunting task. Some of the main applications of NLP are:

We will be using several concepts from these when we analyze unstructured textual data from social media in the upcoming chapters.