Blueprints for Text Analytics Using Python: Machine Learning-Based Solutions for Common Real World (NLP) Applications

From the Preface

Approach of the Book

This book is intended to support data scientists and developers so they can quickly enter the area of text analytics and natural language processing. Thus, we put the focus on developing practical solutions that can serve as blueprints in your daily business. A blueprint, in our definition, is a best-practice solution for a common problem. It is a template that you can easily copy and adapt for reuse. For these blueprints we use production-ready Python frameworks for data analysis, natural language processing, and machine learning. Nevertheless, we also introduce the underlying models and algorithms.

We do not expect any previous knowledge in the field of natural language processing but provide you with the necessary background knowledge to get started quickly. In each chapter, we explain and discuss different solution approaches for the respective tasks with their potential strengths and weaknesses.

Thus, you will not only acquire the knowledge about how to solve a certain kind of problem but also get a set of ready-to-use blueprints that you can take and customize to your data and requirements.

Each of the 13 chapters includes a self-contained use case for a specific aspect of text analytics. Based on an example dataset, we develop and explain the blueprints step by step.

The choice of topics reflects the most common types of problems in our daily text analytics work. Typical tasks include data acquisition, statistical data exploration, and the use of supervised and unsupervised machine learning. The business questions range from content analysis (“What are people talking about?”) to automatic text categorization.