About

Welcome to uClassify.com! We want to share classifier technology with everyone. We recognized that classifiers are mostly present at universities research departments and expensive commercial companies. We want to change that. We want everyone to have the possibility to use a top notch classifier - completely free. We find it enormously exciting to see what happens when a tool for creativity is given to the community. We hope to see all kinds of beyond-our-imagination classifiers and incredible web applications being built around the API.

API

By using the API you can easily build applications using an advanced classification engine without having to be a scientist.

Contact

We have created a uClassify google group for support and other discussions! If you want to reach via e-mail or phone, please don't hesitate to contact us with any feedback, questions or inquires. Or give me a call on +46-(0)70-6179559 (Jon Kågström, Sweden).

People

At the moment we are three people working on this project. We are all situated in Stockholm, Sweden.

Jon Kågström

I have been working with text classification since 2004, it all started with my master thesis. Another project I have is Codeode where I developed Cactus Spam Filter which uses the same classification technology.

Roger Karlsson

Roger Karlsson focuses on classifier server stability, making it thread safe and allowing it to handle a big number of parallel calls. Roger likes c++. A lot. He is also the founder of kephyr.com.

Emil Kågström

Emil is my brother and is a C#, database and web expert. He does this on his valuable spare time. Sometimes I wonder if SQL or Swedish is his mother language. One of his other sites is kipnic.com - an ajax.net, asp.net, web 2.0 resource.

FAQ

What is a text classifier?

A text classifier answers the question "To which predefined category is this text most likely to belong?" For example a classifier trained on web categories can answer "I am by 99% certain that the web page belongs to the category food."

What does it mean to train a classifier?

Before it can classify anything will require some training. Training involves creating all wanted classes (categories) and training each class on text documents that are of that type. For example creating a web page categorizer would require that some classes are created (food, cars, news, health etc). Then each class is trained on documents that are of that type. E.g. putting texts about food into the food category, car texts into the car category and so on.

Is there a restriction on the number of calls per day?

It's too early to say at this point of the project, we suspect that if uClassify becomes popular we may have to introduce some limit.

Is it really free?

Yes it is completely free. The only thing we ask for is that you link back to us from your web site.

But can I use your API for commercial purposes?

Yes! Do your best monetize your cool classifications, just remember to link back to us!

Creative Commons License
Classifications by uClassify is licensed under a Creative Commons 3.0 Unported License.