Slashdot Mirror
Project Anonymizes Your Writing Style To Hide Your Identity
mikejuk writes "An open source project to combat 'stylometry,' the study of attributing authorship to documents based only on the linguistic style they exhibit, is proving that it is possible to change writing style to evade detection. Artificial Intelligence techniques are routinely used to detect plagiarism and recently were employed to reveal that Harry Potter author J. K. Rowling is indeed the author of The Cuckoo's Calling, which was published under the byline of Robert Galbraith. Now software is tackling the opposite problem — anonymizing writing style to protect the identity of the originator. The JStylo-Anonymouth (JSAN) framework is a work in progress at the Privacy, Security and Automation Lab (PSAL) at Drexel University. It analyzes a written text and detects features which could be used to identify the author. It then suggests changes that need to be made to avoid the author's stylistic fingerprint appearing in the work."
How will it disguise my terrible opinions that are obviously wrong?
Uhm, what? It was revealed by someone at Rowlings agency tweeting it to a Sunday Times reporter, after the reporter commented on how good it was for a debut novel - that has all been confirmed by the agency.
Unless the above line is badly phrased and is meant to say "recently were employed to confirm prior reports that..." - it didn't reveal anything of the sort, the link had already been revealed by plain old journalism.
A million college students are waiting anxiously for this tool now that some professors have started checking their essays electronically for plagarism.
If Slashdot were chemistry it would look like this:Cadaverine
Profit does. When your bottom line depends on keeping schools convinced that you're indispensable in the War On Plagiarism you damn well find plagiarism everywhere you can, whether or not it's actually there. There are approximately 80 MILLION students in the US, with our education system being as repetitive and formulaic as it is it becomes a virtual certainty that out of 80,000,000 students a significant number will say the same thing the same way.
A bullet may have your name on it but splash damage is addressed "To whom it may concern."
I am sorry, but as far as literature goes, writing style anonymization (is that a word?) would harm the original intent of the author. A literary work is valuable (when so) due to author's style, among other factors, much like in movies, where a certain actor's voiceover is best for a certain character. The same character would become retarded if the actor's voice changes. Imagine Donkey (from Shrek) played by Morgan Freeman or Darth Vader played by Danny de Vito. Good characters, good actors, no match in style and intent.
Yeah, students would love this in their paper, but literature? Hell, no.
...gis sdrawkcab (usually not responding to ACs; don't bother posting as AC)
... in the rest of your digital life.
In light of recent events -and I'm not only referring to the NSA-gate, but also to all the known ways to get your private information- it is hard for me to figure out a digital way of keeping your identity secret in a high profile incident.
This is he next step in surveillance, if he government isn't doing it already. Binding together various accounts of yours based on statistics of phrases.
And it's redundant since they have a database of all IP connections, web pages, and stuff you type in anyway. Sigh. I suppose it will make confirmation of these AI. techniques trivial. Yey.
(-1: Post disagrees with my already-settled worldview) is not a valid mod option.
Surely one could simply auto-translate their prose into another language and back to avoid stylometric identification?
So, can any mediocre author convert his story to the style of a known good author using this?
-- Senior Software Engineer, Attorney appearance services, locallawyerapp.com.
Just don't lick the envelope.
Sounds like some company is trying to toot their own horn here or something, but AI didn't out J.K. Rowling. Her lawyers friend did. http://www.businessinsider.com/russells-apologizes-to-jk-rowling-2013-7
Stephen King seems to agree with you.
In his book "On Writing", he explains (among many other good points) that one hallmark of good writing is finding the right combination of words for imagery.
He uses examples like "I lit a cigarette, tasted like a plumber's handkerchief'" from Raymond Chandler and "'It was darker than a carload of assholes' by George V Higgins.
The Odyssey (IIRC) has the phrase "it was a wine dark sea", so this has been around for a very long time.
For casual writing the project may be useful, but I wonder how much imagery will be lost in translation.
Many of the works of revolutionaries, radicals, and dissenters are memorable for their specific imagery. Simon Sinek analyzed "I have a dream", and noted the difference between "I have a dream" and "I have a plan". The two are very different, and have different effects on people. (Viz. TED talk "How Great Leaders Inspire Action")
I'm doubtful that AI has progressed to the point where the mood and emotional content will be preserved in such a translation.
To be effective, defiant writing will still require courage.
This is a dupe from yesterday: http://tech.slashdot.org/submission/2852793/post-without-worry---anonymouth-hides-your-identity?sdsrc=rel
An excellent point, I will try to remember this in future writing. It's the sort of thing you don't get in a writing course, for which I am grateful.
Thanks.
Dear aunt, let's set so double the killer delete select all
Well, there's spam egg sausage and spam, that's not got much spam in it.
Right here. :)
Looks like a typical web toy, so I wouldn't quit your job and start working on your Great American Novel based on the results.
It was confusingly worded in TFA. What I eventually figured from it is that it was not used as a discovery mechanism. It looks like it was a test they performed after it was revealed, and the test only confirmed that she was the author.
It was not done to uncover any hidden truths, it was done to demonstrate the correctness of the tool.
John
Way back, in the dim, distant past of the bucolic walled gardens that preceded the Internet as we know it ... there was AOL. AOL had walled predator-free gardens within gardens, where only teens younger than 18 were supposed to be communicating.
There were rumors that evil pedophiles were lurking in these gardens, so I made a sub-account for a totally bogus 16-year old boy named Alex. And Alex went forth to play.
All was going well, Alex was quite a popular young man amongst his peers and had lured ZERO pedophiles when he got this e-mail from a fellow writer: "Alex, are you Tsu?"
BUSTED ... not because of subject matter or vocabulary, but because of a @#$&%^ liking for compound, complex sentences and other arcane constructions ... and using them accurately.
Which person posted this?
There is simply not enough data in your post to find that out. You would probably have to write a few paragraphs of text in your natural style to give the algorithm any real chance.
Also, you think this is going to identify people that type very little? Or have multiple personalities, bipolar disorders or similar?
No, it probably can't. And there's likely to be many, many other scenarios in which it cannot detect the writer reliably. So what? It doesn't have to be completely perfect to be useful.
JStylo-Anonymouth (JSAN)?! Could you possible have come up with any more clunky name than that? ;) Damn, I should set up some agency just to create punchy names for all these projects.