Exploring emotional preference for smartphone applications

Emotion is an essential element of human behaviours. In this research, we investigated human behaviours related with the touch interface on a smartphone as a way to understand users' emotional states. As modern smartphones have various embedded sensors such as accelerometer and gyroscope, we aim to utilize data from these embedded sensors for recognizing human emotion and further finding emotional preferences for smartphone applications. We collected 12 attributes from 3 sensors during users' touch behaviours, and recognized seven basic emotions with off-line analysis. Finally, we generated a preference matrix of applications by calculating the difference between prior and posterior emotional states to the application usage. The pilot study showed 0.57 of an average f1-measure score (and 0.82 with decision tree based methods) with 455 cases of touch behaviour. We discovered that a simple touching behaviour has a potential for recognizing users' emotional states.