Scientists Create Algorithm So Your Smartphone Could Tell You When You're Bored
Smartphones will soon be able to detect whether the users are getting bored after a group of experts have come up with an algorithm. A test on the prediction of the algorithm points to an impressive accuracy of up to 83 percent.
The development of the algorithm was carried out by researchers from the Telefonica Research in Barcelona, Spain and the University of Stuttgart, Germany.
According to reports, the group took into consideration several factors, which include time, degree the phone is used by the person, as well as how long it had been since the user received a message or a call.
Initially, the researchers created the Borapp Android application to collect indicators of boredom among users at different times of the day. The survey was carried out for a period of two weeks.
The group asked 54 respondents, via its developed application, to indicate the levels of boredom they experienced at various times of the day. The responses they generated were run against data from the overall consumption of the phone. These data include the number of apps used by the user as well as how often the phone was accessed.
It is worth noting from what the researchers have found out that users tend to use more apps as well as accessed their phones more often when they are bored.
The researchers then built another app - dubbed the Borapp 2 - to check the accuracy of the algorithm. The study involved 16 participants.
"Results from a second ﬁeld study with 16 participants suggest that people are more likely to engage with recommended content when they are bored, as inferred by our boredom-detection model," reads [pdf] the paper created by the researchers, entitled When Attention is not Scarce - Detecting Boredom from Mobile Phone Usage.
Specifically, the respondents who were deemed by the algorithm as bored were more likely to click on the Buzzfeed link sent to them.
"We chose the Buzzfeed app as suggested content, because (1) the app caches articles, so that the study did not rely on permanent availability of an Internet connection, and (2) its content is designed to be interesting to a broad audience," states the paper.
The paper will reportedly be presented at the ACM International Joint Conference on Pervasive and Ubiquitous Computing next week which will take place in Osaka-Japan. The paper will receive the "Best Paper Award."
Researchers include Martin Pielot, Jose San Pedro, Nuria Oliver from the Telefonica Research and Tilman Dingler from the University of Stuttgart, Germany.
Sean MacEntee | Flickr