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

Turning text into valuable information is essential for many businesses looking to gain a competitive advantage. There have many improvements in natural language processing and users have a lot of options when choosing to work on a problem. However, it’s not always clear which NLP tools or libraries would work for a business use—or which techniques you should use and in what order.

This practical book provides theoretical background and real-world case studies with detailed code examples to help developers and data scientists obtain insight from text online. Authors Jens Albrecht, Sidharth Ramachandran, and Christian Winkler use blueprints for text-related problems that apply state-of-the-art machine learning methods in Python.

If you have a fundamental understanding of statistics and machine learning along with basic programming experience in Python, you’re ready to get started. You’ll learn how to:

• Crawl and clean then explore and visualize textual data in different formats
• Preprocess and vectorize text for machine learning
• Apply methods for classification, topic analysis, summarization, and knowledge extraction
• Use semantic word embeddings and deep learning approaches for complex problems
• Work with Python NLP libraries like spaCy, NLTK, and Gensim in combination with scikit-learn, Pandas, and PyTorch