I’m a writer. So I like to write about writing. I have also compiled a list of Writing Resources, which I may update from time to time.
So here’s a very fun tool. I Write Like analyzes “your word choice and writing style,” then compares it to the writing of famous authors. How many authors are in the IWL database? How many of the famous authors’ texts have been analyzed? I have no idea. But there was enough data to give me three different results from three different texts.
When comparing a block of text from this post.
When comparing a block of text from this post. And…
Ah….there we go. This was the result when I entered text from this, the most popular post on my site. I honestly don’t see the similarities at all, but who am I to argue with an algorithm?
Stylometric identification exploits the fact that we all have a ‘fingerprint’ based on our stylistic choices and idiosyncrasies with the written word.
Here is a very interesting study about how algorithms are being used to uncover anonymous authors by studying writing style. It’s fascinating — but potentially scary stuff.
In his “Concluding Thoughts,” white paper co-author Arvind Narayanan had this to say:
We’ve thrown open the doors for the study of writing-style based deanonymization that can be carried out on an Internet-wide scale, and our research demonstrates that the threat is already real. We believe that our techniques are valuable by themselves as well.
The good news for authors who would like to protect themselves against deanonymization, it appears that manually changing one’s style is enough to throw off these attacks. Developing fully automated methods to hide traces of one’s writing style remains a challenge. For now, few people are aware of the existence of these attacks and defenses; all the sensitive text that has already been anonymously written is also at risk of deanonymization.