Thursday, September 3, 2015

Smartphones Now Capable Of Detecting Boredom

It sometimes seems like our phones can do literally anything. I mean they can make appointments for us, wake us up in the morning, remind us of things, help us search for things on the internet, take pictures, record videos, etc... and now, it seems, we can add boredom detector to that list. That's right, according to researchers, an algorithm has been developed that can tell if you are bored by looking at your mobile activity. The algorithm considers factors like the time since you last received a call or text, the time of day it is, and how much you are using your phone.

The research was conducted by several people at Telefonica Research in Barcelona, Spain and will be presented at the UbiComp ubiquitous computing conference in Japan. The researchers determined that looking at this kind of data gives a reliable prediction of boredom as often as 83% of the time. In addition to that, the researchers also sent bored smartphone users an alert to check a BuzzFeed article. This was to judge that people who were bored clicked on the link more often than those who weren't.

Granted, it is a bit tough using a machine to infer a person's state of mind, however being able to do so with a smartphone could be very powerful. Let's say an app were able to predict that you were bored and also knew your location, it could then attempt to feed you content that it things you would like to see. One startup has already started trying something similar. Triggerhood has built software that allows apps to collect data about how the smartphone is being used and then determines when the best time is to send the user a notification.

The researchers at Telefonica first determined characteristics of boredom by using an Android app that surveyed participants, asking them to rate their boredom multiple times a day for two weeks. These responses were compared to other data that was taken from phones measuring how many apps the user used and how intensely the phone was used overall. Both of these measures increased as the users became more bored.

To validate the algorithm, the researchers built another Android app that determined, on its own, whether or not the user was bored. When it did this it sent an alert to the user's phone asking if they wanted to read a Buzzfeed article on the site's news app. A separate set of participants used this app for two weeks and researchers determined that people who identified as bored were more likely to click on the alert and read the story.

University of Stuttgart Graduate Student and Co-Author of the paper Tilman Dingler worked on the study  as a visiting researcher at Telefonica last year. Dingler says that the researchers now want to find out more about what kinds of content people might want to see the most of when they are bored and whether or not that might include learning activities.

The biggest problem here is getting people to use an app or service that analyzes this much data about them. In addition to that, there is also the question of how accurately researchers can predict boredom due to the fact that they received their data by asking people to repeatedly report how bored they were. Assistant Professor of Computer Science at the University of Rochester M. Ehsan Hoque believes that this may not accurately represent "true boredom" as our mental states are usually subconscious. Regardless, Hoque says that he is excited about the promise of the study as it shows that researchers are looking the mental state of people through smartphone data. "We know boredom leads to depression, so if you can infer the person is bored, you can do something about it," Hoque concludes.

Content originally published here
Sharing this story on Social Media? Use these hashtags! #Smartphones #Boredom #Telefonica

No comments:

Post a Comment

AirCards and Mobile HotSpot Rentals