I Write Like - Analyzes Writing Style

I Write Like is a website that analyzes your writing and suggests a writer your style is similar to.

The result is an answer like this:

You are then given a block of code that lets you put a badge on a webpage. 

I sent the author an email and asked about the underpinnings of the website.

"Hi, Stumbled across your website and am intrigued. Could you tell me a bit about your algorithm? I am a software developer and have a podcast called Swampcast. You might enjoy the session with Pandora's Tom Conrad."

Dmitry Chestnykh immediately wrote back "Hi Michael,

Thanks! You can read about it here:
It’s also open source:
Dmitry lives in Montenegro and has written several journaling products. He wrote I Write Like as a way to publicize his software. As it sometimes happens, his idea went viral. 
The program is currently written in Racket, and uses a Bayesian classifier to make the writing comparisons based on just a few factors: "the number of words in sentences, the number of commas, semicolons, and whether the sentence is a direct speech or a quotation".
It's an interesting program and a good way to learn about Racket. 

Views: 74

Comment

You need to be a member of Codetown to add comments!

Join Codetown

Happy 10th year, JCertif!

Notes

Welcome to Codetown!

Codetown is a social network. It's got blogs, forums, groups, personal pages and more! You might think of Codetown as a funky camper van with lots of compartments for your stuff and a great multimedia system, too! Best of all, Codetown has room for all of your friends.

When you create a profile for yourself you get a personal page automatically. That's where you can be creative and do your own thing. People who want to get to know you will click on your name or picture and…
Continue

Created by Michael Levin Dec 18, 2008 at 6:56pm. Last updated by Michael Levin May 4, 2018.

Looking for Jobs or Staff?

Check out the Codetown Jobs group.

 

Enjoy the site? Support Codetown with your donation.



InfoQ Reading List

OpenJDK News Roundup: Compact Source, Module Import Declarations, Key Derivation, Scoped Values

There was a flurry of activity in the OpenJDK ecosystem during the week of April 14th, 2025, highlighting eight new JEPs having been elevated from their JEP Drafts to Candidate status. Four of these will be finalized after their respective rounds of preview.

By Michael Redlich

Redis 8 Targets AI Applications with New Data Type for Vector Similarity

Redis has recently announced the addition of Vector Set, a data type designed for vector similarity and a new option for AI applications. This new data type marks the first major contribution from Salvatore Sanfilippo (aka ‘antirez’), the creator of Redis, since rejoining the company.

By Renato Losio

Architecture is Designing Knowledge Flow – Diana Montalion at Explore DDD

At the Explore DDD conference, Diana Montalion said software architecture is about designing for knowledge flow, with the goal of software teams learning more about the system they are building. This contrasts with the traditional focus on knowledge stock, which is about information that is already known. She sees effective architects as librarians, helping disseminate knowledge.

By Thomas Betts

How GitHub Built Sub-Issues into Its Issue Tracking System

Coinciding with the generally availability of sub-issues, GitHub engineer Shaun Wong shared insights about how they added support for hierarchical issue structures, the lessons learned during development, and the key role sub-issues played in their workflow.

By Sergio De Simone

AWS Introduces MCP Servers for AI-Assisted Cloud Development

AWS has launched the open-source Model Context Protocol (MCP) Servers, revolutionizing AI-powered code assistants. These servers enhance development speed and security, ensuring adherence to AWS best practices. With features like automated Infrastructure as Code and cost insights, MCP democratizes AWS expertise and empowers developers to optimize cloud solutions effortlessly.

By Steef-Jan Wiggers

© 2025   Created by Michael Levin.   Powered by

Badges  |  Report an Issue  |  Terms of Service