Feasible Affect Recognition in Advertising based on Physiological Responses from Wearable Sensors

抄録

Recent studies in affective computing have facilitated and stimulated the development of systems and sensors that can recognize and interpret human affects. Affective computing has been applied in various domains, and one of the applied domains is in the marketing area to increase the consumers' appeal and attraction. In particular, advertisements (ads) can convey amounts of information in a short time. Therefore, using physiological responses can help to acquire a user's feedback and obtain an advantage. This study proposes non-invasive affect recognition in each scene of an advertising video using electroencephalogram (EEG), electrocardiogram (ECG) and eye-tracking. The preliminary analysis of EEG shows the relationship between scene feeling score and emotional affects regarding physiological responses. Hence, we also trained two types of recognition models: window recognition and sequence learning. The models learned from the physiological responses and questionnaires on a user's preference in each ad scene.