Modelling risk perception using a dynamic hybrid choice model and brain-imaging data: An application to virtual reality cycling

•Joint use of electroencephalography (EEG) and virtual reality in the cycling context.•Developed hybrid choice model using dynamic data in virtual reality.•Demonstrated potential of the employment of neural data (alpha wave) in a hybrid model framework as an indicator of risk. Road risk analysis is one of the key research areas in transport, where the impact of perceived risk on choices, especially in a dynamic setting, has been long recognised. However, due to the lack of dynamic data and the difficulty in capturing risk perception, existing studies typically resort to static and stated approaches to infer the experienced level of risk of individuals. In this paper, we aimed to address this research gap through developing a hybrid choice model that jointly employed dynamic data on cycling behaviour in virtual reality and neural data to evaluate how the fluctuations in momentary risk perception influence the behaviour of cyclists. The results of the developed model confirm our hypotheses, demonstrating that cyclists reduce their speed when approaching a junction as the potential for a collision with passing cars increases. Moreover, the latent component allowed us to establish a link between the neural data, the amplitude of alpha brainwaves, and objective risk measures. In line with our hypothesis, we found that decreased alpha amplitude is associated with higher perceived risk, which in turn increases the likelihood of braking. The implications of our study are manifold. On the one hand, it shows the ability of virtual reality to elicit complex cyclists’ behaviour and the feasibility of a joint collection of dynamic neural and choice data. On the other hand, we demonstrated the potential of the employment of neural data in a hybrid model framework as an indicator of risk that allowed us to gain a better understanding of cycling behaviour and associated neural processing. These promising findings pave the way for future studies that aim to explore the advantages of neuroscientific inputs in the choice models.