Automatic facial expression recognition systems can provide information about our emotions and how they change over time. However, based on different statistical methods the results of automatic systems have not yet been compared. In the current paper we evaluate the emotion detection between three different commercial systems (i.e. Affectiva, Kairos and Microsoft) when detecting dynamic and spontaneous facial expressions. Even if the study was performed on a limited sample of videos, the results show significant differences between the systems for the same video and per system across comparable facial expressions. Finally, we reflect on the implications according the generalization of the results provided by automatic emotion detection.
Previous research has found that stigma can be a barrier to service use but there has been little work examining actual service encounters involving members of stigmatized groups. One such group are those with problematic or unmanageable debts. Providing advice to members of this group is likely to be particularly difficult due to the stigma associated with being in debt. Using conversation analysis and discursive psychology, this study examines 12 telephone advice conversations between debt advisors and individuals in debt. Both clients and advisors oriented to the negative moral implications of indebtedness and typically worked collaboratively to manage these issues. Clients often claimed a moral disposition as a way to disclaim any unwanted associations with debt, but could find it difficult to reconcile this with an insolvency agreement. Moreover, the institutional requirements of the interaction could disrupt the collaborative management of stigma and advisors could manage the subsequent resistance from clients in either client‐centred or institution‐centred ways. The findings suggest that the products offered by debt advice agencies, as well as the manner in which they are offered to clients, can either help or hinder debtors negotiate the stigma‐related barriers to service engagement.
A growing literature has found a link between performance-related pay (PRP) and poor health, but the causal direction of the relationship is not known. To address this gap, the current paper utilises a crossover experimental design to randomly allocate subjects into a work task paid either by performance or a fixed payment. Stress is measured through self-reporting and salivary cortisol. The study finds that PRP subjects had significantly higher cortisol levels and self-rated stress than those receiving fixed pay, ceteris paribus. By circumventing issues of self-report and self-selection, these results provide novel evidence for the detrimental effect PRP may have on health.
Despite the popularity of physiological wearable sensors in sport activities to provide feedback on athletes' performance, understanding the factors influencing changes in athletes' physiological rhythms remains a challenge. Changes in physiological rhythms such as heart rate, breathing rate or galvanic skin response can be due to both physical exertion and psychoemotional states. Separating the influence of physical exertion and psychoemotional states in activities that involves both is complicated. As a result, the influence of psycho-emotional states is usually underestimated. In order to identify the specific influence of psycho-emotional states in physiological rhythm changes, 28 participants were asked to participate in a zipline activity, which involve little or no physical exertion while stimulating psycho-emotional states. By using nonlinear analyses, results show that specific changes in phys-This research was supported and led by Sensum Ltd. in collaboration with Queen's University Belfast.
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.