In future, your smartphone will know when you're bored

Metaratings
02 Sep 2015
00:00
Article

ITEM: A group of researchers at Telefonica Research in Barcelona say they’ve developed an algorithm that can basically help your smartphone know when your bored, and push you content to fix that.

According to Technology Review, the machine-learning algorithm works by analyzing your smartphone activity and including factors such as time of day, how intensely you use apps, and how long it’s been since you had a phone call or text message:

For their study, the Telefonica researchers first determined characteristics of boredom by using an Android app to ask study participants to rate their level of boredom several times a day over two weeks. The responses were compared with other data snagged from the phones measuring things like how many apps they used, and how intensely the phone was used overall (both measures rose as people got more bored).To validate the resulting algorithm, researchers built another Android app that concluded on its own whether the user was bored, and, when it did, sent an alert to their phone asking if they wanted to read an article on BuzzFeed’s news app. A separate set of study participants used it for two weeks, and researchers found that the people who’d been identified as bored were more likely to click on the alert to see the story, and to spend time looking at it, than those who were randomly sent an alert. For their study, the Telefonica researchers first determined characteristics of boredom by using an Android app to ask study participants to rate their level of boredom several times a day over two weeks. The responses were compared with other data snagged from the phones measuring things like how many apps they used, and how intensely the phone was used overall (both measures rose as people got more bored).To validate the resulting algorithm, researchers built another Android app that concluded on its own whether the user was bored, and, when it did, sent an alert to their phone asking if they wanted to read an article on BuzzFeed’s news app. A separate set of study participants used it for two weeks, and researchers found that the people who’d been identified as bored were more likely to click on the alert to see the story, and to spend time looking at it, than those who were randomly sent an alert.

The researchers claim that they were able to accurate predict boredom 83% of the time, although the TR report points out that the researchers had an edge in asking participants to tell them how bored they were first.

Presumably the level of accuracy in a real world scenario will be similar to how, say, personalized push ads or Amazon’s recommendation engines work – the more data they have on you, the more accurate the results. (Which I mention because personally, I'd have to be pretty damn bored to click on a BuzzFeed link.)

TR says the researchers will present their study at the UbiComp conference in Japan next week.

Related content

Tags:
Comments
No Comments Yet! Be the first to share what you think!