TimmyHWEBSITES TO SUIT EVERYONE
June 12th 2008 01:15
It’s almost impossible to create a website experience that appeals to everyone. Some people respond to images, other to text on a blank page, Generation Y loves flash and the Baby Boomers crave facts, figures, charts and graphs.
Researchers at MIT’s Sloan School of Management are hoping to create a website that will automatically adapt to each visitor, making them valuable marketing products. This sort of innovation could mean that the presentation of online information is presented to complement a person’s style of thinking.
The initial results suggest that such measures might be able to increase a site’s sales by as much as 20 percent. The Sloan System would be able to adapt the style of a webpage to suit a user by analysing a short pattern of clicks. Some sites like Amazon.com have attempted similar “Smart Websites” but they have utilised stored cookies and lengthy questionnaires which users find intimidating.
Professor of marketing at the Sloan School, John Hauser, says that websites running the Sloan system will be able to detect and adjust to a user’s cognitive style. "Suddenly, you're finding the website is easy to navigate, more comfortable, and it gives you the information you need," Hauser says. “The user shouldn't even realize that the website is personalised.”
A prototype of the website, was produced recently for British Telecom’s Broadband service. The initial page that a user sees lets him/her choose to compare plans using a chart or to interact with a broadband advisor.
"You can see here that someone who's very analytic is probably more likely to go to 'compare plans' than to the direct advisor," says Hauser. Within about 10 clicks, the system makes a guess at the user's cognitive style and morphs to accommodate. "If we determine that you like lots of graphs, you're going to start seeing lots of graphs," he says.
"If we determine that you like to get advice from peers, you're going to see lots of advice from peers."
The system would also track data over time to see which versions of the website work most effectively for which cognitive styles, assisting in reducing the number of clicks necessary to capture the user’s style.
Peter Brusilovsky, director of the personalised adaptive Web systems lab at the school of information sciences at the University of Pittsburgh, says that in most cases this sort of cognitive recognition has been used for education, not for e-commerce. “What is possible to do automatically is just impossible to do through the user, since users typically have little time to invest, and may not really be sophisticated [about how to adapt a page the way they want],” he says.
One of the most notable applications could be for mobile internet technology. These are generally hard for users to personalise because of limited bandwidth, but the Sloan School’s system would make this much simpler.
Much of the system relies firstly on matching users to others who have visited the site and used similar click patterns. Bamshad Mobasher associate professor in the school of computer science at DePaul University says that a lot of other work in the area has been limited to this first stage. But the Sloan system adds a psychological dimension that makes the task more challenging for a website's designers. It will be interesting to see whether that approach turns out to be better than measuring users' past behaviour alone like in Mabasheran’s systems.
The team plans to build a full version of its system for the Japanese Suruga Bank.
The researchers will watch website users for cultural attitudes as well as for cognitive style. They expect to discover whether visitors have a hierarchical or egalitarian view of society. As opposed to thinking in terms of what is good for the individual or what is good for the collective.
It could be that a person's tendency to think individually or collectively might influence which features of a product are most emphasised and therefore most effective. The team says global companies might one day be using website morphing techniques to build single websites that can adapt to users based on their cultural background, as well as on their cognitive style.
Researchers at MIT’s Sloan School of Management are hoping to create a website that will automatically adapt to each visitor, making them valuable marketing products. This sort of innovation could mean that the presentation of online information is presented to complement a person’s style of thinking.
The initial results suggest that such measures might be able to increase a site’s sales by as much as 20 percent. The Sloan System would be able to adapt the style of a webpage to suit a user by analysing a short pattern of clicks. Some sites like Amazon.com have attempted similar “Smart Websites” but they have utilised stored cookies and lengthy questionnaires which users find intimidating.
Professor of marketing at the Sloan School, John Hauser, says that websites running the Sloan system will be able to detect and adjust to a user’s cognitive style. "Suddenly, you're finding the website is easy to navigate, more comfortable, and it gives you the information you need," Hauser says. “The user shouldn't even realize that the website is personalised.”
A prototype of the website, was produced recently for British Telecom’s Broadband service. The initial page that a user sees lets him/her choose to compare plans using a chart or to interact with a broadband advisor.
"You can see here that someone who's very analytic is probably more likely to go to 'compare plans' than to the direct advisor," says Hauser. Within about 10 clicks, the system makes a guess at the user's cognitive style and morphs to accommodate. "If we determine that you like lots of graphs, you're going to start seeing lots of graphs," he says.
"If we determine that you like to get advice from peers, you're going to see lots of advice from peers."
The system would also track data over time to see which versions of the website work most effectively for which cognitive styles, assisting in reducing the number of clicks necessary to capture the user’s style.
Peter Brusilovsky, director of the personalised adaptive Web systems lab at the school of information sciences at the University of Pittsburgh, says that in most cases this sort of cognitive recognition has been used for education, not for e-commerce. “What is possible to do automatically is just impossible to do through the user, since users typically have little time to invest, and may not really be sophisticated [about how to adapt a page the way they want],” he says.
One of the most notable applications could be for mobile internet technology. These are generally hard for users to personalise because of limited bandwidth, but the Sloan School’s system would make this much simpler.
Much of the system relies firstly on matching users to others who have visited the site and used similar click patterns. Bamshad Mobasher associate professor in the school of computer science at DePaul University says that a lot of other work in the area has been limited to this first stage. But the Sloan system adds a psychological dimension that makes the task more challenging for a website's designers. It will be interesting to see whether that approach turns out to be better than measuring users' past behaviour alone like in Mabasheran’s systems.
The team plans to build a full version of its system for the Japanese Suruga Bank.
The researchers will watch website users for cultural attitudes as well as for cognitive style. They expect to discover whether visitors have a hierarchical or egalitarian view of society. As opposed to thinking in terms of what is good for the individual or what is good for the collective.
It could be that a person's tendency to think individually or collectively might influence which features of a product are most emphasised and therefore most effective. The team says global companies might one day be using website morphing techniques to build single websites that can adapt to users based on their cultural background, as well as on their cognitive style.
| 73 |
| Vote |
subscribe to this blog
