Just two words can identify the author of an email

Forensic linguists are rarely first at a crime scene, but their evidence can sometimes swing an entire case. The field focuses on the analysis of language, sometime distinguishing between people's unique writing styles.

Historically that has been difficult to do with any degree of confidence. But new research from Nottingham Trent University claims that it's actually possible to identify the author of an email with as few as two words.

Please review

David Wright, from the university's School of Arts and Humanities, took thousands of emails from the US energy firm Enron that have been released into the public domain and compared how often employees used particular two to six word phrases.

Wright found that the way people use these phrases is unique to them, influenced by the different speech and writing that they're exposed to during their lifetime. In testing, his technique was able to correctly identify a particular author 95 percent of the time when a sample was longer than 1000 words.

For example, when one lawyer's messages were compared against 175 other employees, Wright found that he tended to use two phrases in particular: "a clean and redlined version", and "please review and let's discuss."

Let's discuss

"The repetitiveness of these phrases shows that the individual has developed their own tried and tested phrases, which they know will work to get a job done while working in their role of a lawyer," said Wright.

"This shows that when faced with written evidence in cases, of which authorship is disputed, clues to the writer's identity can reside in small, common, everyday phrases. This may lead to improving the reliability of evidence given to the courts, and ultimately the delivery of justice."

The full details were published in a paper in the International Journal of Corpus Linguistics.