Fifty shades of frustration: Intra- and interindividual variances in expressing frustration

Negative emotions like frustration can lead to risky driving behavior in manual driving and may hinder the acceptance of innovative automated vehicles. The option to automatically recognize such negative emotions of vehicle users with so called affect-aware systems has gained increasing attention within the last few years. This offers the possibility to adapt vehicle functions, such as the human-machine interface, in real-time. Emotional expressions in face and body form po-tential indicators for user frustration. Previous studies have investigated expressions of frustration in the context of driving and mobility, but have neglected situational and interindividual dif-ferences. In this paper, we examined the possibility to improve the recognition of frustration by considering individual differences. For this, a driving simulator study with 50 participants and a real-world driving study with 23 participants were conducted. An analysis of participants' facial expressions during frustrating driving situations confirms previously reported expressions of frustration (Brow Lowerer, Dimpler, Brow Raiser, Smile and Lip Press). In addition, the results also hint towards high variance between and low variance within participants for all other ex-pressions, suggesting the existence of individual-typical expressions of frustration. Hence, future frustration-aware systems could benefit from considering these individual differences by using a universally trained algorithm that is then customized towards each individual.