LAUSR

Mostly, statisticians and allied researchers resort to quantitative studies inwhich numerical data are involved. Lately, with the computer oriented professional life of the twenty-first century, researchers could easily practice text based analysis as it is popularly resorted in qualitative studies. This book is an excellent source for its concepts, tools and illustrations. A case in point is the debates on whether some (not all) Shakespearean dramas were written by someone other than Shakespeare and such disputes are resolvable using text analytics. Sometimes, it is called text data mining. There are 16 well written chapters covering a range of topics such as origins and timeline of text analytics, benefits of text analysis, text analytics process, deductive versus inductive content analysis, unit of analysis, basics of sampling, coding versus categorization, planning process, text preprocessing, standardization versus cleaning, stemming versus lemmatization, inverted index, term-document matrix, frequency weighting, latent semantic analysis, singular value decomposition, decision making, cluster analysis, random forests, Dirichlet versus correlated models, classification versus machine learning, naïve Bayes, support vector machines, sentiment analysis, storytelling concepts, visualization techniques, illustration of R, Python and SAS languages among others. This well written book has five parts and they are data mining based text analytics versus content analysis, data preparation and planning process, machine learning versus cluster analysis, data storytelling and software programmes to uncover information. Some salient features in this book are up-to-date core references in each chapter. I enjoyed reading this book. I recommend this book to sociologists, qualitative researchers, statistics and computing professionals.