Text Analysis with R

Matthew L. Jockers is Professor of English and Data Analytics as well as Dean of the College of Arts and Sciences at Washington State University. He leverages computers and statistical learning methods to extract information from large collections of books. Using tools and techniques from linguistics, natural language processing, and machine learning, Jockers crunches the numbers (and the words) looking for patterns and connections. This computational approach to the study of literature facilitates a type of literary “macroanalysis” or “distant reading” that goes beyond what a traditional literary scholar could hope to study. Dr. Jockers’s most recent book, The Bestseller Code (2016, with Jodie Archer), has earned critical praise, and the algorithms at the heart of its research won the University of Nebraska’s Breakthrough Innovation of the Year in 2018. In addition to his academic research, Jockers has worked in industry, first as Director of Research at a data-driven book industry startup company and then as Principal Research Scientist and Software Development Engineer in iBooks at Apple, Inc. In 2017, he and Jodie Archer founded “Archer Jockers, LLC,” a text mining and consulting company that helps authors develop more successful novels through data analytics. In late 2019, Jockers and others founded a new text mining startup focused on helping independent authors (“indies”). Rosamond Thalken is an Instructor of English and Digital Technology and Culture at Washington State University. Her research engages questions about the intersections and impacts among digital technology, language, and gender. She currently teaches College Composition and Digital Diversity, a course which analyzes the cultural contexts within digital spaces, including intersections of race, gender, class, and sexuality. In 2019, Thalken finished her Master’s degree in English Literature at Washington State University. Her thesis combined text analysis and close reading to explore the female Supreme Court Justices’ rhetorical strategies for reinforcing ethos in court opinions.

• Part I Microanalysis.- 1 R Basics.- 2 First Foray into Text Analysis with R.- 3 Accessing and Comparing Word Frequency Data.- 4 Token Distribution and Regular Expressions.- 5 Token Distribution Analysis by Chapter.- 6 Correlation.- 7 Measures of Lexical Variety.- 8 Hapax Richness.- 9 Do it KWIC.- 10 Do it KWIC(er) (And Better).- Part II Metadata.- 11 Introduction to dplyr.- 12 Parsing TEI XML- 13 Parsing and Analyzing Hamlet.- 14 Sentiment Analysis.- Part III Macroanalysis.- 15 Clustering.- 16 Classification.- 17 Topic Modeling.- 18 Part of Speech Tagging and Named Entity Recognition.- Appendices.- Index.- List of Tables.- List of Figures.