In today’s multi media world, consumers can turn to any number of sources for news – TV, newspapers, or the internet.
News editors are being pressured to maximise the number of people reading, hearing or viewing the material they offer.
Bernardo Huberman, HP Labs’ senior fellow and director of HP’s Social Computing Lab, and colleague Fang Wu, think that they have come up with a way to help.
They have created a tool that could dramatically increase the attention paid to every item on a media organisation’s internet homepage.
Called i-catcher, it dynamically charts the attention paid to each piece of online content on a particular page – from news articles to videos and banner ads. It can suggest where and for how long any individual item should be offered on that page to maximise the total number of views that each item receives.
Behind i-catcher, said Huberman, is a complex algorithm that balances novelty with popularity. ‘We all attend to things online because they are new or popular. Eventually attention fades, and we attend to other things that are new or popular.’
By factoring trends, i-catcher can help editors avoid keeping an item on a page after interest in it has waned, as well as giving new items a chance to come to prominence.
If the articles are not proving interesting to anyone, i-catcher will suggest moving them lower down the page or removing them altogether much more quickly than conventional editorial practices would dictate.
In the future, i-catcher may not only be employed by media organisations, but by groups with retail web sites such as HP.
The basic algorithm would need to be tweaked, Huberman noted. Technology products are novel for weeks rather than a few hours, for example, and HP might want to use criteria such as available inventory or profit margins in deciding which items to favour.
‘But it will still tell us what items we need to move up the page to maximise the attention these items receive in total,’ he said.