Blueprints for Text Analytics Using Python

by Jens Albrecht, Sidharth Ramachandran, Christian Winkler

Turning text into valuable information is essential for businesses looking to gain a competitive advantage. With recent improvements in natural language processing (NLP), users now have many options for solving complex challenges. But it's not always clear which NLP tools or libraries would work for a business's needs, or which techniques you should use and in what order.

This practical book provides data scientists and developers with blueprints for best practice solutions to common tasks in text analytics and natural language processing. Authors Jens Albrecht, Sidharth Ramachandran, and Christian Winkler provide real-world case studies and detailed code examples in Python to help you get started quickly.


Extract data from APIs and web pages
Prepare textual data for statistical analysis and machine learning
Use machine learning for classification, topic modeling, and summarization
Explain AI models and classification results
Explore and visualize semantic similarities with word embeddings
Identify customer sentiment in product reviews
Create a knowledge graph based on named entities and their relations

Genres: Programming

402 pages, Paperback

Published January 12, 2021

Reviews

[Walter Ullon · Rating 5 out of 5]

This book delivers on what it sets out to do: provide ready-made code blueprints for various NLP tasks using Python. It was straightforward about its mission and didn't promise to make me "an expert in 11 short chapters!". And for that I am grateful.

It is the most up-to-date resource that I've come across that implements some of the latest advancements in the literature of NLP.

The second half of the book is much better than the first, which is mostly basic stuff that most people with some NLP exposure would be well-acquainted with. But they are perfectly paced for any beginner. It is a great start.

Chapters 4-11 cover name-entity-recognition, sentiment analysis, knowledge graphs, LDA models, text summarization, and a lot more. What's more, the code just works which is something that is not always the case with other publishers. The code snippets are very borrowable, which is a plus.

Highly recommended!

[Stein Karlsen · Rating 5 out of 5]

Great overview of different problems with a detailed solution for a wide range of use cases in handling text

[Evan · Rating 5 out of 5]

Exceptionally useful book for those who are looking for starter code for their NLP project.

[Ashraf Hesham · Rating 5 out of 5]

Very recommended especially for NLP beginners.