Blog > June 2008

One of the double-edged side-effects of the process of ‘locking on’ to a new brand is a certain engagement with low-grade spam-generation-pornography.

New brands are being requested and added to the tracking system all the time, some demanding initial work in order to set the classifier on the right tracking path.

For example, there is a stationary producer named ‘Avery Dennison’. The thing is, in order to pick up its ‘everyday’ mentions in the informal areas of the web – blogs, etc., – we need to track it in its short-hand: ‘Avery’. And so here come the exclusion terms: bird-related content must not get a look in – and then there is ‘Tex Avery’ – creator of Daffy duck, ‘Roger Avery’ – co-writer of Pulp fiction, and Cardinal Avery Dulles, an outspoken fire-brand.

Now this type of ‘dirty’ pick-up is dealt with by adding an exclusion term or two, but what happens when the tracking of ‘Avery’ means we start picking up the whitest of noises – a common typo, and when this, in turn, means an over-abundance of porn?

Simply with the elision of the indefinite article and a certain adverb (via a forgotten space-bar) ‘a very…’ has become ‘avery’. And we are picking it up. This isn’t so interesting in itself – it just involves a bit of extra set-up work – except that this typo-effect has resulted in the massive pick up of spam-cum-porn sites.

This unholy alliance of spam-generated text and pornographic material is coming in thick and fast. But it is useful: it represents quite a test for the classifier, and particularly in its initial setting-up. And so, ultimately, it is used in a positive way.

In a little time all these backgrounds of white noise – from Tex Avery to parasitic porn pages – all this will be excluded as we learn better how to read them, and the brand ‘Avery’ will get tracked in a proper and meaningful sense. Only then can this brand’s performance on the web be charted and compared to rival brands.