What’s going on?

The last three weeks I’ve been doing some other things than working on uClassify.com. I really needed a break to regenerate some energy and inspiration. During this period I’ve been talking to Roger Karlsson about what we should develop next on uClassify.

uClassify HTML forms

We know that there are a lot of cool classifiers being built but not many of them finds their way to the public in a web application. We believe that the reason is the last barrier – using the API and to do that you need to write code. Our plan is to allow users who doesn’t have the time to learn and use the uClassify API, to simply copy and paste a HTML form snippet to any site.

We also want to publish some uClassify code libraries in different languages. One of our users, Alex Popescu, is currently implementing a Python library.

TrollGuard

In the beginning of January we released TrollGuard, a free WordPress spam filter plugin that uses uclassify.com. So far we have not had many users but recently it was featured on KillerStartups.com and since then we have an increasing number of users.

A very big thank you to Pacuraru Ovidiu who has given incredibly good feedback which led to an upgrade. We are looking forward to receive more feedback from all of you as our goal is to make the best spam filter plugin.

Using published classifiers

We’ve just implemented so that everyone with a uClassify account (free) can access public classifiers.

Once a classifier is published everyone can use it via the GUI or the web API and in return authors get a link to their website from everyone who use their classifiers. This should hopefully inspire more people to share their cool classifiers!

As an example of a published classifier check out the mood classifier by prfekt.se. Here is the list of all published classifiers.

Bloggparti.se – is text left or right wing? (Swedish)

A new site called bloggparti.se (only works for Swedish blogs/texts) using uClassify has spread through the Swedish blogosphere. The site takes a blog or text and tests it to see how it resembles to the major Swedish political parties.

Mattias Aspelund from 49lights.com created this classifier using 100 tagged blogs from each party. The site was created within 24 hours and had more than 1000 requests on the first day.

We think it’s very exciting to see how quickly people can build cool applications around uClassify. Self test sites seems to be very popular for bloggers, for example genderanalyzer.com went from 0 to Google Page Rank 6 in just three months.

I know there are more applications being built right now, looking forward to see those in action!

TrollGuard – protects your blog from spam comments

Me and Roger have just finished TrollGuard – an anti-spam plugin to WordPress 2.7 or later.

The plugin is in Beta and we are aware of some lacking features – however we would greatly appreciate if someone out there wanted to do some testing for us and come back with feedback!

This has been a small sideproject we did during our Christmas holidays using the uClassify API. We think it’s really cool that in less than a week we were able to setup a new Akismet service. Previous uClassify web applications have mostly been for entertainment, this plugin will acctually do something helpful – protect blogs from spam comments.

We are also confident in the accuracy of TrollGuard as similar classification technology has been used in Cactus Spam Filter since 2004.

Well now it’s up to you to test it! What isn’t working? What features are missing? Let us know!

Check TrollGuard out!

We moved to Amazon EC2 after a big crash

During Christmas some unfortunate events occurred – on the 26th of December Ultimahosts (who we were paying to maintain our servers) had a crash and managed to wipe out all our servers. This was very frustrating, but I expected it to be online again soon, recovered from their backups.

On the 28th they let me know that they had accidentally destroyed all backups. How is it possible for a single datacenter to screw up so much?? I don’t know.

Most classifiers are intact and users registered 17-25 can be recovered

Luckily I had taken manual backups myself – one on all the classifiers on the 25th of December and one on the user database on the 17th of December. This means that most classifiers are intact, but users who registered between 17-25 of December are gone. You guys can re-register with the same username and I will attach it to your old classifiers (send me an e-mail). I am really sorry about this and for the inconvenience it has caused.

New servers on Amazon EC2

I spent over 60 hours reinstalling and moving uclassify to Amazon EC2. This feels really good (now that it’s done). We can easily scale and we have an own good backup system using Amazon EBS + daily offsite backups.

I’m really sorry for any inconvenience,

Jon Kågström

Ps. Thanks to Google cache I was able to recover all posts for this blog…

LibraryThing annouces uClassify competition

On LibraryThing you can add your own books to a personal library. By doing this you start to get recommendations from either other users who has read the same book or automatically by the system. There are also several forums where users can discuss books – just like a really really big book club. At the time I signed up there were over 34 million books added. I added a couple of books I have recently read and to my surprise all of them already existed in the system, even the Swedish ones. After adding them I was immediately getting lots of recommendations, such as “The Satanic Verses” and “Robot : mere machine to transcendent mind”. Really cool!

Now with all these books some kind of categorization could help.

Competition

LibraryThing are encouraging their users to create something cool with uClassify. The prize is $100 Amazon gift certificate and Toby Segaran’s “Programming Collective Intelligence”. LibraryThing also presents a couple of cool ideas which you can use such as fictional vs non-fiction. The competition ends on February 1 2009 so what are you waiting for?

Buzz & Development

Yesterday we were mentioned on ReadWriteWeb which generated a lot of visits and more importantly – classifiers. 30 new classifiers were created within a time period of 10 hours, even though many are just created out of curiosity to quickly test the system – some will hopefully mature and have web applications built around it.

What’s going on techwise

As you have noticed we are continuously improving our system by carefully adding new features. The following tasks are planned for the GUI

We are soon installing a new more flexible menu system.

Users will be able to create profiles with descriptions and links. Also classifiers should be able to have a link to the web site it’s implemented.

Better information about training – right now there is no feedback on how much training has been done or is required. We want to give users an idea of how the training data performs.

What’s going on commercialwise

Everything is free on uClassify and that is how it will stay.

Our commercial idea is to offer companies the possibility to buy their own classification servers. For large databases with texts that needs to be classified it’s intractable to send every text for a roundtrip to uclassify.com. Instead companies could be interested in doing this efficiently locally. A products page with server information will appear soon.

What’s your mood?

Today, 2 months after our launch, our users have created over 200 classifiers. Most are unpublished and under construction. PRfekt, the team behind the popular Typealyzer, recently published a new classifier that determines the mood of a text – whether a text is happy or upset. You can try it for yourself here!

So lets test some snippets!

Jamis is (justly) upset and writes:

Is anyone else annoyed by the “just speak your choice” automation in so many telephone menus? I feel like an idiot mumbling “YES!” or “CHECK BALANCE!” into my phone. Maybe it’s the misanthrope in me coming to the front, but I’d much rather push buttons than talk to a pretend person.

The mood classifier says 98.1% upset.

Spam is no fun either, or as Ed-Anger notes:

“I’m madder than a rooster in an empty hen house at Internet spammers and I won’t take it anymore. Those creeps clutter up my e-mail with their junk, everything from penis enlargement pills to some lady telling me she’ll give me a million dollars if I’ll help her get her money out of Africa. “Rush me 10 grand quick as possible and we’ll get the whole thing started,” she says.”

The mood classifier says 97.0% upset.

Now over to some happy blogs, amour-amour has a confesion:

“I love my iphone in a way I never thought possible!! When my fiance got his and spent 23 hours gazing at it lovingly, uploading (or is it downloading??) apps and buying accessories for it I put it down to him just being a technology geek.”

The mood classifier says 79.8% happy.

Finally Nitwik Nastik comments a Rickey Gervais:

“This is a hilarious stand-up routine by British Comedian Ricky Gervais on Bible and Creationism. It’s really funny how he ridicules the creationist stories from the book of Genesis (the book of genesis can be found here)and point out to it’s obvious logical blunders. Sometimes it may be difficult to understand his accent and often he will make some funny comments under his breath, so try to listen carefully.”

The mood classifier says 69.7% happy.

The author recommends at least two hundred words (more text than my samples) which seems reasonable!

GenderAnalyzer thoughts

First, thanks to everyone who is testing GenderAnalyzer, we have had incredible feedback. We received emails from many people that are facinated and a few that thinks it sucks =) GenderAnalyzer is still generating a lot of traffic and people are blogging about it.

Our learnings

Determining the gender of an author is not easy, besides the classification there is a chain of technical events that must work in order to get a reliable result. As many of you have noticed the accuracy has dropped to 53% which is far lower than expected based on our tests. There may be several reasons for this low accuracy and I will mention some of them here.

  • Our trainingdata of 2000 blogs is automatically collected from blogspot. Runing internal tests (10 fold cross validation) on this data gives us an accurcy of 75% this effectivly means “Given that the corpus is a perfect representation of real world data, the classifier is able to give any real world data the correct label by a chance of 75%”. So our trainingdata is probably not very representative, as a matter of fact it’s very stereotypical (see for yourself here). Using data from all kind of sources should give us a better model.
  • When someone is testing a blog we are not crawling through posts on the blog to get a good amount of text. We are only hitting the given url and using the text (and html) that appear there as test data. So a page with mostly images or frames will give bad test data. Does anyone know a nice library that – given an url crawls blog posts? Via RSS perhaps?
  • We are trying to encode test data to utf-8 which is the format of the training data – it could be that we are missing some encodings.
  • And of course – the difference between male and female writing is not significant?

What’s next?

We are currently collecting a new set of training data that is much more representative. We will switch to this classifier during the next week and start a new poll for it. It’s going to be very exciting!

GenderAnalyzer showdown + server upgrade

Today genderanalyzer.com was featured on BoingBoing this resulted in that our server could not handle all the requests. We have now upgraded the server and it should be happy to serve all requests.

While the server was unable to respond to all requests – accuracy in the poll dropped from 63% to 55% (since the error message makes people vote that it’s not guessing right). However now the accuracy is slowly recovering!

Sorry for any inconvenience this might have caused.