What is Text Analytics?

Introduction

The Text Analytics API is a cloud-based service that provides advanced natural language processing over raw text and includes the following four main functions:

• Sentiment Analysis
• Key Phrase Extraction
• Named Entity Recognition
• Language Detection

This service is a part of one of the cognitive services from Microsoft Azure. Let us quickly discuss these four use-cases and then we’ll start with their implementation.

Recently, the text analytics service has been renamed “Language” service in Azure.

Sentiment analysis

With sentiment analysis, we can find out what people think of our brand or topic by mining the text for clues about positive or negative sentiment.

The service provides sentiment labels (such as negative, neutral, and positive) based on the highest confidence score found by the service at a sentence and document level. This feature also returns confidence scores between 0 and 1 for each document & sentences within it for positive, neutral, and negative sentiment.

Key phrase extraction

We can use key-phrase extraction to quickly identify the main concepts in the text. For example, in the text “The food was delicious and there was wonderful staff”, the Key Phrase Extraction will return the following main talking points:

• food
• wonderful staff

Language detection

Language detection can detect the language an input text is written in and report a single language code for every document submitted on the request in a wide range of languages. The language code is associated with a confidence score.

Named entity recognition

Named Entity Recognition (NER) can identify and categorize entities in your text as people, places, organizations, quantities, etc. Well-known entities are also recognized and linked to more information (usually Wikipedia) on the web.

Creating a Text Analytics resource

Now that we understand the use-cases of this service, let’s go ahead and create the service in Azure.