Background: Emotion recognition technology plays the essential role of enhancement\nin Human-Computer Interaction (HCI). In recent years, a novel approach for emotion\nrecognition has been reported, which is by keystroke dynamics. This approach can be\nconsidered to be rather desirable in HCI because the data used is rather non-intrusive\nand easy to obtain. However, there were only limited investigations about the\nphenomenon itself in previous studies. This study aims to examine the source of\nvariance in keystroke typing patterns caused by emotions.\nMethods: A controlled experiment to collect subjectsââ?¬â?¢ keystroke data in different\nemotional states induced by International Affective Picture System (IAPS) was\nconducted. Two-way Valence (3) Ã?â?? Arousal (3) ANOVAs were used to examine the\ncollected dataset.\nResults: The results of the experiment indicate that the effect of emotion is\nsignificant (p < .001) in the keystroke duration, keystroke latency, and accuracy rate\nof the keyboard typing. However, the size of the emotional effect is small, compare\nto the individual variability.\nConclusions: Our findings support the conclusion that the keystroke duration,\nkeystroke latency, and also the accuracy rate of typing, are influenced by emotional\nstates. Notably, the finding about the size of effect suggests that the accuracy rate\nof the emotion recognition could be further improved if personalized models are\nutilized. On the other hand, the finding also provides an explanation of why real-world\napplications which authenticate the identity of users by monitoring keystrokes may not\nbe interfered by the emotional states of users. The experiment was conducted using\nstandard instruments and hence is expected to be highly reproducible.
Loading....