A performance comparison of eight commercially available automatic classifiers for facial affect recognition

In the wake of rapid advances in automatic affect analysis, commercial automatic classifiers for facial affect recognition have attracted considerable attention in recent years. While several options now exist to analyze dynamic video data, less is known about the relative performance of these classifiers, in particular when facial expressions are spontaneous rather than posed. In the present work, we tested eight out-of-the-box automatic classifiers, and compared their emotion recognition performance to that of human observers. A total of 937 videos were sampled from two large databases that conveyed the basic six emotions (happiness, sadness, anger, fear, surprise, and disgust) either in posed (BU-4DFE) or spontaneous (UT-Dallas) form. Results revealed a recognition advantage for human observers over automatic classification. Among the eight classifiers, there was considerable variance in recognition accuracy ranging from 48% to 62%. Subsequent analyses per type of expression revealed that performance by the two best performing classifiers approximated those of human observers, suggesting high agreement for posed expressions. However, classification accuracy was consistently lower (although above chance level) for spontaneous affective behavior. The findings indicate potential shortcomings of existing out-of-the-box classifiers for measuring emotions, and highlight the need for more spontaneous facial databases that can act as a benchmark in the training and testing of automatic emotion recognition systems. We further discuss some limitations of analyzing facial expressions that have been recorded in controlled environments.

The Effectiveness of Somatization in Communicating Distress in Korean and American Cultural Contexts

Previous research has documented that Asians tend to somatize negative experiences to a greater degree than Westerners. It is posited that somatization may be a more functional communication strategy in Korean than American context. We examined the effects of somatization in communications of distress among participants from the US and Korea. We predicted that the communicative benefits of somatic words used in distress narratives would depend on the cultural contexts. In Study 1, we found that Korean participants used more somatic words to communicate distress than US participants. Among Korean participants, but not US participants, use of somatic words predicted perceived effectiveness of the communication and expectations of positive reactions (e.g., empathy) from others. In Study 2, we found that when presented with distress narratives of others, Koreans (but not Americans) showed more sympathy in response to narratives using somatic words than narratives using emotional words. These findings suggest that cultural differences in use of somatization may reflect differential effectiveness of somatization in communicating distress across cultural contexts.

Affective science perspectives on cancer control: strategically crafting a mutually beneficial research agenda

Cancer control research involves the conduct of basic and applied behavioral and social sciences to reduce cancer incidence, morbidity, and mortality and improve quality of life. Given the importance of behavior in cancer control, fundamental research is necessary to identify psychological mechanisms underlying cancer risk, prevention, and management behaviors. Cancer prevention, diagnosis, and treatment are often emotionally laden. As such, affective science research to elucidate questions related to the basic phenomenological nature of emotion, stress, and mood is necessary to understand how cancer control can be hindered or facilitated by emotional experiences. To date, the intersection of basic affective science research and cancer control remains largely unexplored. The goal of this article is to outline key questions in the cancer control research domain that provide an ecologically valid context for new affective science discoveries. We also provide examples of ways in which basic affective discoveries could inform future cancer prevention and control research. These examples are not meant to be exhaustive or prescriptive but instead are offered to generate creative thought about the promise of a cancer research context for answering basic affective science questions. Together, these examples provide a compelling argument for fostering collaborations between affective and cancer control scientists.

Comment: Constructionisms?

Constructionism can take several forms: one can refer to biological, psychological, or social constructionism. What I want to argue in this article is that if one carefully teases out varied forms of constructionism, the frontiers between some of them will begin to blur.