In this new post from Ian Barber he takes a look at something that can come in very handy when you need something a bit more complex than the standard search results - term weighting.

The term weighting and ranking function is at the core of any information retrieval system. The vector space model with the cosine similarity is maybe the best known and most widely used, but there are plenty of alternatives. We're looking at two here, the BM25 function based around a probabilistic model, and a function based around language modeling.

He's put together a few examples on some basic weighting practices - simple string evaluation based on word occurrence, using the Okapi/BM25 method and language modeling with a little bit of probability and scoring involved.

On the Programming and Management blog today, Nick Halstead has posted a quick look at how to make the AuctionAd$ you include on your site a bit more dynamic.

Before you read the rest of the article (you may not be interested in the coding side) the end result is that I have built an AuctionAd$ display system that adjusts the keywords it uses based upon the visitor clicking adverts. This means that your visitors will automatically adjust what is displayed for them by clicking or not clicking on the adverts shown.

You still have control over the keywords you use but, instead of a supplying a single keyword, you supply a list that it initially selects from and then adapts based on your visitors interaction.

He shows his method - grabbing the keyword information from a SQL database that has a weighting system based on the number of mouseovers for the ad for that keyword. The information is stored in a SQL database and is updated dynamically via an ajax request.

On the Programming and Management blog today, Nick Halstead has posted a quick look at how to make the AuctionAd$ you include on your site a bit more dynamic.

Before you read the rest of the article (you may not be interested in the coding side) the end result is that I have built an AuctionAd$ display system that adjusts the keywords it uses based upon the visitor clicking adverts. This means that your visitors will automatically adjust what is displayed for them by clicking or not clicking on the adverts shown.

You still have control over the keywords you use but, instead of a supplying a single keyword, you supply a list that it initially selects from and then adapts based on your visitors interaction.

He shows his method - grabbing the keyword information from a SQL database that has a weighting system based on the number of mouseovers for the ad for that keyword. The information is stored in a SQL database and is updated dynamically via an ajax request.