icon bookmark-bicon bookmarkicon cameraicon checkicon chevron downicon chevron lefticon chevron righticon chevron upicon closeicon v-compressicon downloadicon editicon v-expandicon fbicon fileicon filtericon flag ruicon full chevron downicon full chevron lefticon full chevron righticon full chevron upicon gpicon insicon mailicon moveicon-musicicon mutedicon nomutedicon okicon v-pauseicon v-playicon searchicon shareicon sign inicon sign upicon stepbackicon stepforicon swipe downicon tagicon tagsicon tgicon trashicon twicon vkicon yticon wticon fm
16 Dec, 2015 03:10

‘Smart’ websites may soon know how you’re feeling – through your mouse

‘Smart’ websites may soon know how you’re feeling – through your mouse

Clicks, shares, and other data are vital for online marketers, but a new study by Brigham Young University offers a glimpse into a future where the mouse or cursor reveals something more personal: the user’s own emotions.

Three separate experiments carried out by computer scientists found negative feelings can be tracked by cursor motions – useful information for online businesses that have to guess what is driving away potential customers. The researchers discovered that dissatisfaction or confusion led to slower, shorter, more irregular and less precise mouse movement.

“Using this technology, websites will no longer be dumb,” head researcher and Brigham Young University information systems professor Jeff Jenkins said in a statement. “Websites can go beyond just presenting information, but they can sense you. They can understand not just what you’re providing, but what you’re feeling” – and all in real-time.

The new technology will help customer service respond more quickly and marketers to make subliminal changes to a user’s web experience if negative emotions are getting in the way of potential clicks or engagement, according to the study published in the Management Information Systems Quarterly.

The first experiment involved 65 random users of Mechanical Turk, a crowd-sourced marketplace by Amazon, who were purposely frustrated by a special task. When their feelings got the best of them, their cursor speeds slowed and distances shortened, which Jenkins acknowledged was counterintuitive.

The next exercise faked an e-commerce site and monitored 126 would-be online shoppers. Judging from their mouse behavior, the BYU team identified negative emotions with 81.7 percent accuracy.

The final analysis included an unwieldy online tool to customize products, with which 80 people verbalized annoyance as they piloted their cursor. This provided the researchers with information about not only the type of emotion expressed, but also how deeply that emotion was felt.

“Traditionally it has been very difficult to pinpoint when a user becomes frustrated, leading them to not come back to a site,” Jenkins told BizReport. “Being able to sense a negative emotional response, we can adjust the website experience to eliminate stress or to offer help.”

Jenkins told Ars Technica that mobile devices were his next target for determining user sentiments.

Realeyes, Affectiva and Emotient are some of the companies already engaged in developing products or services to relay potential clients’ emotions to businesses, using other technologies.