A completely recent predictive typing model can simulate different sorts of users, helping work out ways to optimize how we use our phones. Developed by researchers at Aalto University, the brand new model captures the difference between typing with one or two hands or between younger and older users.
‘Typing on a phone requires manual dexterity and visual perception: we press buttons, proofread text, and proper mistakes. We also use our working memory. Automatic text correction functions can assist some people, while for others they will make typing harder,’ says Professor Antti Oulasvirta of Aalto University.
The researchers created a machine-learning model that uses its virtual ‘eyes and fingers’ and dealing memory to type out a sentence, identical to humans do. Meaning it also makes similar mistakes and has to correct them.
‘We created a simulated user with a human-like visual and motor system. Then we trained it hundreds of thousands of times in a keyboard simulator. Eventually, it learned typing skills that may also be used to type in various situations outside the simulator,’ explains Oulasvirta.
The predictive typing model was developed in collaboration with Google. Recent designs for phone keyboards are normally tested with real users, which is expensive and time-consuming. The project’s goal is to enhance those tests so keyboards may be evaluated and optimized more quickly and simply.
For Oulasvirta, this is an element of a bigger effort to enhance user interfaces overall and understand how humans behave in task-oriented situations. He leads a research group at Aalto that uses computational models of human behaviour to probe these questions.
‘We are able to train computer models in order that we do not need commentary of plenty of people to make predictions. User interfaces are in all places today — fundamentally, this work goals to create a more functional society and smoother on a regular basis life,’ he says.
The researchers will present their findings on the CHI Conference in May.
