Child or Adult? Inferring Smartphone Users’ Age Group from Touch Measurements Alone

Abstract

Abstract. We present a technique that classifies users' age group, i.e., child or adult, from touch coordinates captured on touch-screen devices. Our technique delivered 86.5% accuracy (user-independent) on a dataset of 119 participants (89 children ages 3 to 6) when classifying each touch event one at a time and up to 99% accuracy when using a window of 7+ consecutive touches. Our results establish that it is possible to reliably classify a smartphone user on the fly as a child or an adult with high accuracy using only basic data about their touches, and will inform new, automatically adaptive interfaces for touch-screen devices.

Predicting Age Groups from Touch Patterns based on Neuromotor Models

“…Compared with [8] where they get an accuracy rate of 86.5% using one tap task for classification and with a singlesensor aproximation (using smartphone's data), our system performs better, getting a 93.6% of accuracy using only data from smartphones, and over 96% using data from tablets. These results show that our approach, based on drag and drop tasks used to model the neuromotor system of the users, is more discriminative than the scheme from [8].…”

“…However, in our work we demonstrate that using a very common and fast action (e.g. unlock screen based on drag and drop) we can achieve higher classification rates that those achieved in [8] for the one task approach (the second approach have not been implemented yet). In our opinion, both approaches are complementary, have very different nature, and can be combined to achieve higher performances.…”

“…After reducing the number of lognormal signals, the 18 features from [8] are computed for each stroke, and each parameter is averaged across strokes. The 18 averaged parameters are augmented with the task time and the number of strokes to generate the final feature vector of size 20.…”

“…They discovered that children have a larger miss rate than adults when trying to hit small targets. In [8] tap tasks are used to extract time and precisionbased features. They designed two different approaches, using only one tap for classification and using 7 consecutive tasks.…”

Kid on the phone! Toward automatic detection of children on mobile devices

“…Here, we use accuracy as it was used in [56,18,9] and AUC was not reported. Accuracy is computed as the ratio between correct predictions over all predictions of testing samples.…”