The ability to recognize affective states of a person... This paper argues that next-generation human-computer interaction (HCI) designs need to include the essence of emotional intelligence -- the ability to recognize a user's affective states -- in order to become more human-like, more effective, and more efficient. Affective arousal modulates all nonverbal communicative cues (facial expressions, body movements, and vocal and physiological reactions). In a face-to-face interaction, humans detect and interpret those interactive signals of their communicator with little or no effort. Yet design and development of an automated system that accomplishes these tasks is rather difficult. This paper surveys the past work in solving these problems by a computer and provides a set of recommendations for developing the first part of an intelligent multimodal HCI -- an automatic personalized analyzer of a user's nonverbal affective feedback.

This paper discusses the issues pertinent to the development of a meaningful social interaction between robots and people through employing degrees of anthropomorphism in a robot's physical design and behaviour. As robots enter our social space, we will inherently project/impose our interpretation on their actions similar to the techniques we employ in rationalising for example, a pet's behaviour. This propensity to anthropomorphise is not seen as a hindrance to social robot development, but rather a useful mechanism that requires judicious examination and employment in social robot research.

A number of researchers around the world have built machines that recognize, express, model, communicate, and respond to emotional information, instances of ‘‘affective computing.’ ’ This article raises and responds to several criticisms of affective computing, articulating state-of-the art research challenges, especially with respect to affect in humancomputer interaction.

The use of the computer as a model, metaphor, and modelling tool has tended to privilege the ‘cognitive ’ over the ‘affective ’ by engendering theories in which thinking and learning are viewed as information processing and affect is ignored or marginalised. In the last decade there has been an accelerated flow of findings in multiple disciplines supporting a view of affect as complexly intertwined with cognition in guiding rational behaviour, memory retrieval, decision-making, creativity, and more. It is time to redress the imbalance by developing theories and technologies in which affect and cognition are appropriately integrated with one another. This paper describes work in that direction at the MIT Media Lab and projects a large perspective of new research in which computer technology is used to redress the imbalance that was caused (or, at least, accentuated) by the computer itself. 1. Vision The last half-century of technological acceleration has yielded a massive incursion of digital technology into the learning environment, making dramatic differences, and promising even greater changes, to the practice of learning. Computers have served as tools to aid in learning at all levels from simple classroom activities to the way theorists think about thinking. The field of artificial intelligence, with emphasis on ideas such

Abstract not found

It is now easy to find examples of interactive software agents and animated creatures that have the ability to express emotion; this paper describes research for giving them the ability to recognize emotion. The ability to recognize a person 's emotions is a key aspect of human "emotional intelligence," which has been described by a number of scientists as being more important to success in life than are the traditional forms of mathematical and verbal intelligence. This paper describes research underway in emotion recognition at the MIT Media Lab, especially research involving new wearable interfaces. 1 Introduction People often laugh or express delight at something presented by a computer---a funny animation, a virtual pet, a piece of humor mail---even though computers, to date, have been unaware of these human reactions. It is perhaps even more frequent to see a person expressing frustration or irritation at a computer, especially when they feel that the system is hind...

Accurately interpreting and expressing affect is fundamental to empathetic relationships. A platform for sensing and interpreting several aspects of users’ nonverbal affective information and responding through an expressive agent has been developed. The platform includes integration of multi-modal affective sensors with a real time inference engine, a behavior engine, and a 3d scriptable expressive humanoid agent within a graphical virtual environment. Currently the sensors include a pressure-sensitive mouse, a BlueTooth wireless skin conductivity sensor, a TekScan pressure sensor on a chair, and a stereo head tracking system as well as an IBM Blue Eyes infrared-sensitive camera. These sensors feed into custom algorithms for analysis of individual channels of information, such as postural and facial expressions, which in turn are combined with additional channels of information to make an inference about the user’s affective state. The system further synchronizes this sensor data with the agent behaviors and with video of the user and his or her on-screen activity. This platform is seen as a generalpurpose tool applicable to research in several areas, including how to design an affective learning companion, and how to further basic understanding of empathy and emotion contagion in human-agent interaction.

Any opinions expressed here are those of the author(s) and not those of IZA. Research published in this series may include views on policy, but the institute itself takes no institutional policy positions. The Institute for the Study of Labor (IZA) in Bonn is a local and virtual international research center and a place of communication between science, politics and business. IZA is an independent nonprofit organization supported by Deutsche Post World Net. The center is associated with the University of Bonn and offers a stimulating research environment through its international network, workshops and conferences, data service, project support, research visits and doctoral program. IZA engages in (i) original and internationally competitive research in all fields of labor economics, (ii) development of policy concepts, and (iii) dissemination of research results and concepts to the interested public. IZA Discussion Papers often represent preliminary work and are circulated to encourage discussion. Citation of such a paper should account for its provisional character. A revised version may be available directly from the author. IZA Discussion Paper No. 3333

The ways of modelling some of the most profound effects of emotion and arousal on cognition are discussed. Entropy reduction is used to measure quantitatively the learning speed in a cognitive model under different parameters ’ conditions. It is noticed that some settings facilitate the learning in particular stages of problem solving more than others. The entropy feedback is used to control these parameters and strategy, which in turn improves greatly the learning in the model as well as the model match with the data. This result may explain the reasons behind some of the neurobiological changes, associated with emotion and its control of the decision making strategy and behaviour. 1

With the growing use of computers and computing objects in the design of many of the day to day tools that humans use, human-computer intelligent interaction is seen as a necessary step for the ability to make computers better aid the human user. There are many tasks involved in designing good interaction between humans and machines. One basic task, related to many such applications, is automatic classification by the machine. Designing a classifier can be done by domain experts or by learning from training data. Training data can be labeled to the different classes or unlabeled. In this work I focus on training probabilistic classifiers with labeled and unlabeled data. I show under what conditions unlabeled data can be used to improve classification performance. I also show that it often occurs that if the conditions are violated, using unlabeled data can be detrimental to the classification performance. I discuss the implications of this analysis when learning a specific type of probabilistic classifiers, namely Bayesian networks, and propose structure learning algorithms that can potentially utilize unlabeled data to improve classification. I show how the theory and algorithms are successfully applied in two applications related to human-computer interaction: facial expression recognition and face detection.