This book leverages advanced techniques and tools in data science to extend data analysis from numeric and categorical data to textual data. Designed for business analysts, it uses a case study approach to teach skills in extracting insights from text data, supporting business decision-making. Exercises primarily use Excel and R, covering techniques from basic text analytics to sophisticated methods like topic extraction and text similarity scoring.
The course begins with framing analytical questions and exploring analytical tool sets. It progresses through preparing data files, performing word frequency and keyword analysis, and conducting sentiment analysis. Advanced topics include visualizing text data, coding, named entity recognition, and topic recognition in documents. The book also covers text similarity scoring and the analysis of large datasets by sampling.
Throughout this journey, readers will apply the CRISP-DM data mining standard, using companion files with numerous datasets for practical exercises. By the end, participants will have a comprehensive understanding of text analytics, enabling them to derive meaningful insights from textual data to inform business strategies.