New effective technology for identifying anonymous email authors created

Whether the diary will continue or not - no difference. The police of thoughts will get to him anyway. He committed - and if he had not touched the paper with his pen, he would have committed - an absolute crime, containing all the others. Thought crime - that's what it was called. Thought crime cannot be hidden forever. You can dodge for some time, and even not one year, but sooner or later they will reach you.

George Orwell, 1984


Professor of Concordia University (Montreal, Canada) Benjamin Fung ( his personal page ) has created a new effective technology for determining identity based on email texts, which is a proven expert opinion and can be used in court.

Dr. Fung (professor of engineering information systems) and his team used methods that are used in speech recognition and data mining to identify duplicates, i.e. distinctive features of combinations that are repeated in the letters of the suspect.


Analyzing such characteristic features as grammatical and (or) stylistic errors, the register of the text of the letter, the manner of treatment, the number and type of "emoticons", the alignment of the text and its volume, as well as a number of other unique features, Professor Fung claims that he can determine the gender with high probability , nationality, age, level of education of the author of the email, which can be a significant contribution to the process of unique identification of a person in contrast to his IP address. To verify the effectiveness of the new technology, the researchers analyzed Enron Email Dataset, which is a collection of more than 200,000 real letters from 158 employees of Enron Corporation.

Thus, if you want to play a trick on a colleague, you are embarrassed to tell the girl directly about something of vital concern, want to give unobtrusive advice, or if you are just a spammer, then the FBI can very likely come to your home in a short time.

The original news is here .