Assessing Video Advertising Engagement via Nonlinear Intersubject Correlation Analysis of EEG and Eye Tracking Dynamics

A novel framework for assessing engagement through video commercials is presented. Deviating from the current approaches, here we cast the problem as nonlinear intersubject correlation analysis and pursue the collective (i.e. across-participants) treatment of EEG signals and eye-tracking measurements. Regarding brain dynamics, two well-known descriptors, namely spatial covariance and phase locking value, undergo transcription to their ‘hyperscanning’ equivalents. Regarding eye-related measurements, individual paths and pupillometric measurements are summarized at population level. Using data from a recording paradigm, where each participant independently watched a cartoon video interrupted by a commercial clip, we show that our approach can provide signatures of engagement to the content being delivered and reconstruct the level of appreciation of the potential consumers.