Linguistic Fingerprints

**Roger J. Kreuz**

**Estimated Reading Time: 65 to 75 minutes**

Your words leave traces. Not perfect fingerprints, but patterns: the small grammatical words you never notice, the rhythms of your sentences, the way you shift between a work email and a text to a friend. This book explores how researchers, detectives, historians, and courts have tried to read those traces, and what happens when they get it right or wrong.

You will learn why the most common words in English often identify writers better than their favorite phrases. You will see how a statistical method settled a two-century-old dispute about the Federalist Papers, how linguists helped expose a forged medieval document, and how a few unusual phrases in anonymous texts pointed investigators toward a killer. You will also learn why stylometry cannot prove authorship on its own, why the Brontë sisters are nearly impossible to tell apart by word counts, and why identifying a writer is not the same as earning the right to unmask them.

This book is for anyone curious about how language reveals identity. Readers of true crime and literary detective stories will find the cases compelling. Writers, editors, and lawyers will find the methods useful. Anyone who has ever wondered whether a text message really came from the person claiming to send it, or whether a famous author actually wrote the book under their name, will find answers here. Most of all, this book is for readers who want to understand a powerful idea and its limits at the same time.

We have all had the experience of recognizing someone from a single sentence. A friend's email arrives and before you check the sender, you know it is them. A novelist publishes a new book under a pseudonym and reviewers say the prose "feels like" a particular writer. A parent reads a note and instantly knows which child wrote it. This intuition is real, and it points to something genuine about language. People do have habits. They favor certain words, construct sentences in particular ways, and leave patterns behind in everything they write. The question that drives this book is whether those patterns can be measured, compared, and used to answer a practical question: who wrote this? The effort to answer that question is called stylometry, the quantitative analysis of language to identify patterns in writing. It is a field that sits at the intersection of linguistics, statistics, psychology, and forensic investigation. It has been used to settle literary disputes, expose forgeries, catch criminals, and, sometimes, ruin reputations. It has also produced confident-sounding conclusions that turned out to be wrong. The appeal of stylometry is easy to understand. A fingerprint is a nearly perfect identifier. If…