Text Analytics for Corpus Linguistics and Digital Humanities

Text Analytics for Corpus Linguistics and Digital Humanities addresses the question of how big tech analyses and exploits our text data. It invites readers to investigate the differences in textual styles, associations, and trends in documents, or even create a map of a text collection to build a simple QA system themselves.

This book delves into applying state-of-the-art text analytics methods to detect and visualise phenomena in text data. It is firmly grounded in methods from corpus linguistics, natural language processing, text analytics, and digital humanities. Readers will learn to conduct experiments with their own corpora and research questions, underline their theories, quantify differences, and identify specific characteristics.

Each chapter provides detailed case studies and experiments using real-world and open-access corpora from diverse fields such as politics, World English, history, and literature. The results are interpreted thoughtfully, with potential pitfalls highlighted and necessary pre-processing steps explained.

The book demonstrates how to use the programming language R, as well as simple alternatives and complements to R, to perform experiments and create visualisations. It features extensible R-code, recipes, links to corpora, and a comprehensive array of methods.

The introduced methods are versatile, applicable to texts from all disciplines, ranging from history or literature to party manifestos and patient reports.