Bridging the gap between the marketer who must put text analytics to use and data analysis experts, Practical Text Analytics is an accessible guide to the many advances in text analytics. It explains the different approaches and methods, their uses, strengths, and weaknesses, in a way that is relevant to marketing professionals. Each chapter includes illustrations and charts, hints and tips, pointers on the tools and techniques, definitions, and case studies/examples.
Consultant and researcher Steven Struhl presents the process of text analysis in ways that will help marketers clarify and organize the confusing array of methods, frame the right questions, and apply the results successfully to find meaning in any unstructured data and develop effective new marketing strategies.
About the Author
Steven Struhl is Principal at Converge Analytic, a marketing and analytics consulting company based in New Jersey. He has experience in consulting and research, specializing in providing effective, practical solutions based on statistical models of decision-making and behavior. His work addresses how buying decisions are made, understanding consumer groups and their motivations, optimizing service delivery and product configurations, and finding the meaningful differences among products and services.
Table of Contents
01 Who should read this book? And what do you want to do today?
Who should read this book
Where we find text
Sense and sensibility in thinking about text
A few places we will not be going
Where we will be going from here
02 Getting ready: capturing, sorting, sifting, stemming and matching
What we need to do with text
Ways of corralling words
03 In pictures: word clouds, wordles and beyond
Getting words into a picture
The many types of pictures and their uses
Applications, uses and cautions
04 Putting text together: clustering documents using words
Where we have been and moving on to documents
Clustering and classifying documents
05 In the mood for sentiment (and counting)
Basics of sentiment and counting
Missing the simple frame with social media
How do I do sentiment analysis?
06 Predictive models 1: having words with regressions
Understanding predictive models
Starting from the basics with regression
Rules of the road for regression
Divergent roads: regression aims and regression uses
07 Predictive models 2: classifications that grow on trees
Classification trees: understanding an amazing analytical method
Seeing how trees work, step by step
CHAID and CART (and CRT, C&RT, QUEST, J48 and others)
Summary: applications and cautions
08 Predictive models 3: all in the family with Bayes Nets
What are Bayes Nets and how do they compare with other methods?
Our first example: Bayes Nets linking survey questions and behaviour
Using a Bayes Net with text
Bayes Net software: welcome to the thicket
Summary, conclusions and cautions
09 Looking forward and back
Where we may be going
What role does text analytics play?
Summing up: where we have been
Software and you