11.Jun.2010 at 22:35 by Joshua Thijssen
Excellent talk. The app has got lot of potential and I could really use it on my feeds already :)
Rowan Merewood (11.Jun.2010 at 16:45)
Talk at Dutch PHP Conference 2010 (English - UK)
Bayesian filtering is a statistical method invented back in 1764 which many people are familiar with for filtering spam out of email. This talk will look at how we can use Bayesian classification to try and predict the quality of a Twitter message. We will start with how Bayesian classification works and follow it through to a Zend Framework application that allows you to rate the contents of your timeline finishing with some speculation on what can be done with this data.
Quicklink: https://joind.in/1760
Track(s): Uncon (E103)
By clicking this button you are declaring that you are the speaker responsible for it and a claim request will be sent to the administrator of the event.
If the claim is approved you will be able to edit the information for this talk.
Are you sure?
11.Jun.2010 at 22:35 by Joshua Thijssen
Excellent talk. The app has got lot of potential and I could really use it on my feeds already :)
13.Jun.2010 at 09:48 by Andries Mooij
Rowan gave a great talk about his project where he applied Bayesian Filtering to his Twitter timeline. I really enjoyed the open discussion and the jokes in the presentation.
13.Jun.2010 at 14:41 by Ian Barber
Nice practical demonstration of bayesian techniques on real world data. Great presenting style from Rowan as always.
14.Jun.2010 at 18:09 by Martin de Keijzer
Now this is one of those talks I really love, practical example, good interaction with the crowd and really some nice stuff to think about. It was nice to look into existing code, the structure and ofcourse to learn something about the bayesian filter which is applied in many anti-spam solutions.
11.Jun.2010 at 14:15 by Stefan Koopmanschap
Great talk, cool stuff ranging from some theoretic stuff about the bayesian filtering to the practical showing of code and the working application, ending with a nice discussion on possible ways to apply the technology.