The algorithm pretty simple, and you can find it on every computer today. It’s a Bayesian classifier, which is widely used to fight spam on the Internet. Take for example the “Mark as spam” button in Gmail or Outlook. When you receive a message that you think is spam, you click this button, and the internal database gets trained to recognize future messages similar to this one as spam. This is basically how “I Write Like” works: I feed it with the whole text of Frankenstein and tell it, “This is Mary Shelley. Recognize works similar to this as Mary Shelley.” Of course, the algorithm is slightly different from the one used to detect spam, because it takes into account more stylistic features of the text, such as the number of words in sentences, the number of commas, semicolons, and whether the sentence is a direct speech or a quotation.
Do you want to learn more?
We published our source code for everyone to review or reuse.
First of all, writing style doesn’t have a precise definition. People can tell you that a certain author write in this style or that style, but their opinions may differ. Thus, it’s difficult to tell even if a human evaluation of styles is accurate. Of course, algorithmic evaluation is even more complicated.
I Write Like uses a certain statistical analysis of word choice and sentence structure. The initial analysis was performed for each author included in our database. The program calculates the same metrics for your text and then calculates probabilities that tell which author has the most similar metrics.
Such analysis is not 100% accurate. It’s still fun, though.
To contact us, please email to [email protected]