Friday, July 16th, 2010

A Q&A with the Creator of "I Write Like": "The Algorithm is Not a Rocket Science"

AND WHO DO YOU WRITE LIKE, DMITRY?This week's meme is I Write Like, a new website that uses an algorithm of mysterious methodology to tell you which author's work your writing most resembles. You enter some text-"your latest blog post, journal entry, comment, chapter of your unfinished book"-and a split-second later, it spits out the html code for a blog-ready badge: "I Write Like H.P. Lovecraft," or any of the 49 other authors in its database. It's hard science and great literature, together at last! Well, kind of.

I Write Like's science has already been strung up and dissected: Gawker's Max Read inputted Mel Gibson's latest phone rant, got Margaret Atwood and came to an unfavorable opinion; Paste magazine got an "I Write Like Stephen King" badge after entering a few Big Boi rhymes; Margaret Atwood herself pasted in a sample of her own writing and got … Stephen King.

So take the site's web indication of how seriously we should be taking its diagnoses.

Dmitry Chestnykh is the creator of I Write Like. He's a 27-year-old Russian software developer living in Montenegro. His company, Coding Robots, also offers a blog-writing program and an application to keep diaries.

He answered a few of my questions via e-mail Thursday night, explaining how his algorithm is like a spam-detector, how he plans to sustain the site beyond short-lived meme, and why he's totally unqualified to analyze writing but still thinks I Write Like is useful.

[A note: since English is not his first language, he asked me to fix any grammatical or style errors in his answers. He barely made any mistakes, predictably putting the typically pitiful American foreign language skills to shame. I just fixed an awkward construction here and there. Based on I Write Like's calculations, by the way, Chestnykh's writing style here is most like David Foster Wallace.]

How and why did you get into software development as a career?
I think I got my first computer at 13, and after I used it for a few months, I knew I wanted to write programs for it. It's a lot of fun to have something made by you do something for you. While at university I launched my tiny software business and have been working on it full-time since then.

Where did you first get the idea for I Write Like? Was it an idea you discussed/developed with friends, or did you go it alone?
Late at night I was looking for ways to promote my software. I had tried a few marketing things before and was going through a checklist to find what I had missed. Then the idea of making a fun badge came to me. Since most of our (Coding Robots') programs were about writing, I immediately thought of comparing people's writing, and began coding. I hadn't discussed it with anyone before putting it online.

What makes you qualified to analyze literature like this?
Nothing, really. I'm the kind of person who is not qualified in a subject before jumping into it. (Good thing I didn't try to become a medical doctor or a rocket scientist!) This is my way of learning: when I want to do something, I do it, learning along the way.

Who are your favorite authors? Do you read more literature in English or Russian (or other languages)?
I think I read more literature in English. It's hard to name my favorite writers because there are so many of them. To name a few: Gabriel García Márquez (unfortunately, I don't know Spanish yet, so I read his works in Russian translation), Agatha Christie, Stephen King, Ernest Hemingway. But there are many of those whose works I haven't had time to read yet.

How many authors are currently in the database? How did you decide which authors to include?
The current version includes 50 writers. First versions included authors from the bestsellers list on Wikipedia, top downloaded books from The Gutenberg Project (a public library of out-of-copyright books), and the ones I could remember. Later versions included authors suggested by users.

When are you going to add explanations for the algorithm for each author? Why haven't you included this already — why keep it secret?
I wanted to write a blog post about it, and to open-source the code, but haven't had time for it yet, because I've been busy updating the program and handling all the traffic, emails and comments I received. Also, it's really interesting to read how people try to explain the results they got.

Actually, the algorithm is not a rocket science, 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 on my side: I feed it with "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.

There are a lot of works in academia dealing with writing analysis, but I used none of them. I have been contacted by people who research this topic, and received a lot of pointers to interesting works. I'm sure I wouldn't have been able to integrate and figure them out in the three days I had to write this thing, but I will definitely learn more about the subject to improve the program.

Really, what's the point of "I Write Like"? Does it have a useful application or is it just for fun?
I didn't think that there was a big point in it before launching. However, I've been proved wrong: it helps people discover and re-discover writers. There are so many comments like "I write like Ernest Hemingway. I have to read more of his books," or "I write like Chuck Palahniuk. Who? Never heard of him, will read," or "I write like Edgar Allan Poe. Never read anything by him, but now I think I will." It is amazing that this tool can be used for education, so I plan to add information about writers and their books in one of the next versions.

I Write Like is going viral very quickly. Ultimately, what's your goal with the site? How will you sustain it beyond a quick-flash meme?
I'm trying to expand the website to make it the destination for people to learn more about how to be a better writer. I will also add more information about writers, and maybe I'll add features to help people discover interesting authors and books.

Will you be tweaking the software to read any other language besides English? You were immediately called out for having more male than female authors, but no one picked up on the apparent overwhelming majority of English-writing authors.
I planned to launch a Russian version, but postponed it because of the lack of time. Also, I've been offered help to make a Portuguese version.

I just finished reading Sam Lipsyte's "The Ask." He's a master of simple, powerful, unusual sentences. I can see how he's doing what he's doing with language, but mostly I just want to bask in the magic and not analyze it too much in the moment. Has developing software like this changed how you read or lessened some of the magic in fine writing?

It has been only four days since I launched the website, and I haven't read anything since the launch, so it's a bit early to say if it changed how I read.

You've promised subscribers an "awesome" newsletter of writing tips and a free download the 1898 how-to book "A Practical Treatise on the Art of the Short Story" by Charles Raymond Barrett. Why that book? What's one of your awesome writing tips?
I've chosen this particular book because it had so many details in it and a good analysis of short story writing. Also because it's out-of-copyright, so I can redistribute it freely, kudos to The Gutenberg Project. :-) The newsletter is a part of the plan to convert "I Write Like" from a quick-flash meme to something sustainable and useful. I'm not a published writer myself, so I'm not qualified to give people tips (especially since English is not my first language). I will be the editor, and other more knowledgeable people will share their advice on writing. I hope the first issue will come out in August.

Katjusa Cisar is a freelance writer living in Atlanta.

43 Comments / Post A Comment

boyofdestiny (#1,243)

I would settle for "I write like: Anybody That Actually Gets Paid a Living Wage to Write Stuff." But I suppose "David Foster Wallace" is pretty good, too.

saythatscool (#101)

That's what I got too. And this is the sample I used:

love fucking outside. Nothing feels better. My favorite position, you ask? Doggy style on terra firma. There's simply nothing more enjoyable than knees in the grass while you're plowing ass.

Because you see, I loved Eight is Enough as a kid. More specifically, I loved Susan Richardson. And there's that opening scene in the intro when the family is building a human pyramid out in the park and Susan's young body is straining under the weight of the two lighter boys and man, Iwould I just get crazy thinking about that image.

And then I would imagine Susan and I at the park and she would turn to me and say "Cool, let's play pyramid." And then she would get on all fours as my pre-teen body mounted hers. Dominant but lighter on top, coiling for hours in ecstasy as we shared ourselves in that quiet solitude of a public park where nobody ever comes, but us.

Even today, I still imagine Susan beneath me as my shorn scrotum waves frantically in the air outside against a lady's backside. Like a lopsided paddle ball being used by an expert, my scrotum will slap against the soft side of a mons pubis and I will close my eyes softly and imagine my sweet Susan underneath me, if only for a few moments. Invariably my mind will wander to what were doubtlessly perfect, natural, tear-drop breasts with dark protruding areolas that my furtive hands would cup as I kissed the back of her neck. Eventually, as I surrender to orgasm I will find myself torn away from her in my mind's eye. But I will always return, faithful to her as a perfect vision if not a perfect real specimen today.

I miss you, Susan.

deepomega (#1,720)

Aim low and reach the stars, my friend.

boyofdestiny (#1,243)

I don't think the algorithm was wrong there.

saythatscool (#101)

When I plugged this quote in:

"His strong manly hands probed every crevice of her silken femininity, their undulating bodies writhing in sensual rhythm, as he thrust his purple-headed warrior into her quivering mound of love pudding."

the algorhithm said I wrote like Neil Gaiman…

dntsqzthchrmn (#2,893)

You mean "Anybody That Actually Gets Paid a Living Wage to Write Stuff" isn't by DFW?

The introduction to my latest paper on the democratization of Belarus also channeled DFW. "Consider the Mobster?"

saythatscool (#101)

Susan was never a strong swimmer…..

I thought you'd be more interested in just before she swims…

saythatscool (#101)


petejayhawk (#1,249)

The Jack Kemp obit I wrote is written like David Foster Wallace. Yay.

The Nick Adenhart obit I wrote is written like Stephenie Meyer. Boo.

boyofdestiny (#1,243)

I'm morbidly interested in this Twilight-esque Nick Adenhart piece.

keisertroll (#1,117)

Should I even make the prerequisite SPOILER ALERT joke?

deepomega (#1,720)

I wanted to make fun of the implication that there are only 50 writers that one can write like, but on reflection that's probably too many. Let's get it down to 10.

KarenUhOh (#19)

In a quarter mile, I will write like the GPS Lady.

Art Yucko (#1,321)

"I Write Like: Shit; because you went to Art School."

That was easy!

Vulpes (#946)

I write like H.P. Lovecraft. The cyclopean horror who lurks in the non-Euclidean space in my bedroom closet, crooning hymns to eldritch gods as I dream dreams of madness, thinks that's bullshit.

Sam seems like a nice guy and I was impressed at how much publicity he did for The Ask, but the book was a big disappointment.

dntsqzthchrmn (#2,893)

The book is about disappointment?

Oh…so he's a better writer than Kafka then, because when I read The Metamorphosis I didn't turn into a cockroach.

sailor (#396)

Did two samples, first ID'd me as Stephen King, the second James Joyce. Now truly do not know whether to shit or go blind.

KarenUhOh (#19)

I got Kurt Vonnegut and James Joyce. So, I'd like my fucking statuette right now very much please.

dntsqzthchrmn (#2,893)

Aroint! and get in line behind me and Shakespeare.

MollyculeTheory (#4,519)

Based on a few samples, text-me is the babbling, deformed lovechild that results from a tryst between Joyce, Nabokov, and Dan Brown. "My God!" I said "My God!" I will "Harris tweed!"?

KarenUhOh (#19)

I think many of us write a lot of run-on sentences.

areaderwrites (#592)

My official work-i-get-paid-for writing got the David Foster Wallace, and my crap blogging got the H.P. Lovecraft. Confused.

Patrick M (#404)

I put his picture in and it said "How Tony Hendra imagines he still looks" (?)

When are you going to add explanations for the algorithm for each author?

etc. etc. etc.

…Also, it's really interesting to read how people try to explain the results they got.

Translation: It's a fake. It's kind of a phony art project, which will be revealed in a couple of weeks.

MollyculeTheory (#4,519)

Momentarily pleased that my professional writing (in genetics) rated a Margaret Atwood rather than a Stephen King, I began to suspect that she might have "DNA" as a keyword. Experiment:

"Tuna yes yes yes DNA. I like DNA. Repair repair repair. Next we did this other thing. DNA. Tuna yes yes yes DNA. I like DNA. Repair repair repair. Next we did this other thing. DNA. Tuna yes yes yes DNA. I like DNA. Repair repair repair. Next we did this other thing. DNA."

> "I write like Margaret Atwood"!

MollyculeTheory (#4,519)

Addendum: replacing "DNA" with "yes", "turtles", and "DMV", respectively, yields DFW.

I would like to meet somebody who writes like Poe but has never read him.

And also anyone else with sexual fantasies about Susan Richardson.

I would like to meet an obnoxious melodramatic teenager who reads Poe and refrains from writing like him.

Neopythia (#353)

I'm somewhat indifferent as my fiction writing returned a Kurt Vonnegut response. It's not that I dislike him, I think he's one of those authors I caught at the wrong time.

I'm scared to try my professional writing as legal/financial writing would probably break the algorithm

petejayhawk (#1,249)

The first paragraph of "Consider the Lobster" was written like Stephen King.

Annie K. (#3,563)

This was exactly what I wanted to know about that site, so thank you very much indeed.

Eric Stoltz (#3,430)

It says I write like Dan Brown. Disconsolate.

keisertroll (#1,117)

Two DFWs, two Stephen Kings, a William Gibson, and an H.P. Lovecraft. My novel will thus be about a cyberpunk baby with telekinetic powers whose diaper is soaking up boiling water but is too busy live-blogging his futile defense against Cththulu to care.

madmadam (#6,111)

i love it! i have not written in so long. i feel life change as i know it thank you!!

yaya (#6,122)

apparently i write like vladimir nabokov. i don't know if i believe it, but frankly, i'm flattered.

Are you trying to make wanna- be writers suicidal? It says my work blogs are just like Dan Brown and Cory Doctorow…frag.

Robin (#6,859)

I just wrote this off the top of my head and it came back with Stephen King. Hum?

My life has been like a roller coaster in hell! For twenty years and counting, I have yet to get off this crazy ride. Everyday I fall deeper and deeper, plunging ever onward toward the bottom. The only difference in my roller coaster is that it goes up, but it never reaches a peak. Mine is more like a dream where you're falling and falling into an endless valley, only this is part of my every waking moment.

Like the child learning to walk, I fall down with each new step. I stand again but I don't do so firmly, as another wave is coming toward me ready to knock the wind out of my sails. I see others enjoying the ride of life. They bask in love and family. They are living instead of merely existing, as I am being sucked into the black hole day after day. All the while, the gravity demons are laughing at me as I continue to spiral ever downward.

Robin (#6,859)

P.S. Eerie…Stephen King and I share the same birthday. Dodododododo……..

Post a Comment