Engineers looking into better ways to deliver smartphone notifications have established that people's attitudes to notifications change depending on where they are, what they're doing, and how they're feeling – suggesting smartphones should be, well, smarter at delivering the right pings at the right time.
The study, at Rutgers' School of Engineering in New Jersey, looked at 5,000 phone notifications sent to 22 participants over four weeks. This led them to develop a model that can predict how receptive you'll be to a notification according to your personality and current environment.
"Ideally, a smartphone notification management system should be like an excellent human secretary who knows when you want to be interrupted or left alone," explains Janne Lindqvist, assistant professor in the Department of Electrical and Computer Engineering. "We know that people struggle with time management all the time, so a smartphone, instead of being a nuisance, could actually help with things."
The study found that people in a good mood were more willing to be interrupted by notifications than grumpy people, and that people doing intense activities like studying or exercising didn't want to be bothered.
This is one of those studies that confirms something we kind of knew already, but it's useful to have evidence - especially if that evidence leads to a better system. We've all been in the position where our phones are bombarding us with updates at the worst possible time, as well as sadly checking Facebook/Twitter/everything else for news because we're bored in the GP's waiting room. Ideally, the phone would learn to balance, so you get only vital notifications when you're stacked and all of them when you're bored.
The new model uses two metrics to decide whether to interrupt you. Firstly, whether you're available or unavailable (in general. Unavailable would be asleep, for instance). Then, the system grades your interruptability and deals with notifications accordingly. It's not market-ready yet (and would presumably need lots more participants than the current 22), but theoretically the model could be really useful:
"We could, for example, optimise our model to allow smartphone customisation to match different preferences, such as always allowing someone to interrupt you. This would be something an excellent human secretary would know. A call from your kids or their daycare should always pass through, no matter the situation, while some people might want to ignore their relatives, for example.
Ideally, smartphones would learn automatically. As it is today, the notification management system is not smart or only depends on a user's setting, such as turning on or off certain notifications. Our model is different because it collects users' activity data and preferences. This allows the system to learn automatically like a 'human secretary,' so it enables smart prediction."
We fully expect to see 'smartifications' debuted at the launch of the iPhone 15.
Main image: Pexels