E-motional advantage: performance and satisfaction gains with affective computing.
ABSTRACT Emotions are now recognized as complex human control systems, crucial to decision making, creativity, playing and learning. Affective technologies may offer improved interaction and commercial promise. In the past, research has focused on technical development work, leaving many questions about user preferences unanswered. For this user-centered study, 60 participants played a simple 'word ladder' game under different controlled conditions. Using 2 x 2 factorial design, and a Wizard of Oz scenario, half the participants interacted with a system that adapted on the basis of the user's emotional expression and half were told the system could react to their emotional expressions. We established that when using an apparently affective system, users perform significantly better and report themselves as feeling significantly happier. We also discuss behavioral responses to the different conditions. These results are relevant to the design of future affective systems.
- SourceAvailable from: Björn Schuller[show abstract] [hide abstract]
ABSTRACT: Automatic detection of the level of human interest is of high relevance for many technical applications, such as automatic customer care or tutoring systems. However, the recognition of spontaneous interest in natural conversations independently of the subject remains a challenge. Identification of human affective states relying on single modalities only is often impossible, even for humans, since different modalities contain partially disjunctive cues. Multimodal approaches to human affect recognition generally are shown to boost recognition performance, yet are evaluated in restrictive laboratory settings only. Herein we introduce a fully automatic processing combination of Active–Appearance–Model-based facial expression, vision-based eye-activity estimation, acoustic features, linguistic analysis, non-linguistic vocalisations, and temporal context information in an early feature fusion process. We provide detailed subject-independent results for classification and regression of the Level of Interest using Support-Vector Machines on an audiovisual interest corpus (AVIC) consisting of spontaneous, conversational speech demonstrating “theoretical” effectiveness of the approach. Further, to evaluate the approach with regards to real-life usability a user-study is conducted for proof of “practical” effectiveness.Image and Vision Computing. 01/2009;
Conference Proceeding: Facial Expression as an Implicit Customers' Feedback and the Challenges[show abstract] [hide abstract]
ABSTRACT: The human face is rich of information and plays important roles in daily communication such as expressing the emotions nonverbally. Facial expression comes in all varieties. Some are intense and sustained while others are subtle and fleeting. Much progress has been made to build computer systems that recognize facial expression for human computer interaction such as affective computing which apply the automatic facial recognition techniques in human computer interaction where the main idea is that the computer could better adjust its behavior to user's current emotion. Other possible area that could use the advance technology of Facial expression recognition system is the customer satisfaction measurement. The expression of customer being served at the counter is captured to evaluate the satisfaction of the customer. This multimedia approach of customer satisfaction measurement is an alternative of the conventional way of collecting customers' response.Computer Graphics, Imaging and Visualisation, 2007. CGIV '07; 09/2007
- International Journal of Human-Computer Interaction 09/2013; 29(12):798-813. · 1.13 Impact Factor