Emotion recognition is an important research topic. Physiological signals seem to be an appropriate way for emotion recognition and specific sensors are required to collect these data. Therefore, laboratory sensors are commonly used while the number of wearable devices including similar physiological sensors is growing up. Many studies have been completed to evaluate the signal quality obtained by these sensors but without focusing on their emotion recognition capabilities. In the current study, Machine Learning models were trained to compare the Biopac MP150 (laboratory sensor) and Empatica E4 (wearable sensor) in terms of emotion recognition accuracy. Results show similar accuracy between data collected using laboratory and wearable sensors. These results support the reliability of emotion recognition outside laboratory.
Via generative adversarial networks (GANs), artificial intelligence (AI) has influenced many areas, especially the artistic field, as symbol of a human task. In human-computer interaction (HCI) studies, perception biases against AI, machines, or computers are generally cited. However, experimental evidence is still lacking. This paper presents a wide-scale experiment in which 565 participants are asked to evaluate paintings (which were created by humans or AI) on four dimensions: liking, perceived beauty, novelty, and meaning. A priming effect is evaluated using two between-subject conditions: artworks presented as created by an AI, and artworks presented as created by a human artist. Finally, the paintings perceived as being drawn by human are evaluated significantly more highly than those perceived as being made by AI. Thus, using such a methodology and sample in an unprecedented way, the results show a negative bias of perception towards AI and a preference bias towards human systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.