Papers about Agent identity

The development of robots that closely resemble human beings can contribute to cognitive research. An android provides an experimental apparatus that has the potential to be controlled more precisely than any human actor. However, preliminary results indicate that only very humanlike devices can elicit the broad range of responses that people typically direct toward each other. Conversely, to build androids capable of emulating human behavior, it is necessary to investigate social activity in detail and to... Read more

In this paper, we present some initial thoughts on the occurrence of verbal abuse in human-chatterbot interaction within the framework of social-cognition. This thinking is an important step towards the understanding of virtual relationships and the design of socially adept technology. Read more

Chatterbots are computer programs that simulate intelligent conversation. They are situated between games and toys, as their aim is mostly to be entertaining, but the user doesn't have to follow precise rules when playing with the program. Currently business and educational applications have started to emerge as a further development of the idea of intelligent dialog. For the game industry, they come close to the concept of NPC, or Non-Player Character, and they may become... Read more

Imagine a future world where humans and machines will be involved in joint activities requiring social skills. This paper presents an overview of the dawnings of this world, concentrating on chatterbots – computer programs which engage the user in written conversation – and their users. Driving upon Clark’s theory of Language and the psychological theory of self-categorisation by Turner, it presents an analysis of social reactions to chatterbots and a taxonomy of the technology. The... Read more

This paper presents a preliminary analysis of verbal abuse in spontaneous human-chatterbot conversations. An ethnographic study suggested that abuse is pervasive and may reflect an asymmetrical power distribution, where the user is the master, and the chatterbot the slave. We propose that verbal aggression in this setting may be a social norm applied by users to differentiate themselves from the machine in what can be regarded as a form of interspecies conflict. The findings stress... Read more

Training of social interaction skills, particularly for emotionally charged situations is becoming increasingly critical in many professions. In cases such as the medical field, however, conventional real-world or role-playing training is extremely limited or even impossible. An example for this is the treatment of injured children. Therefore, we have developed an e-learning system that uses virtual agent technology to simulate the treatment of and human interaction with a hurt, upset boy and his emotional, easily... Read more

AIML - A recently developed standard for describing knowledge for Robots using XML data structures is introduced. A very large English-based robot knowledge base developed using the standard is described. Many other knowledge-based projects based on other international languages are described. The English-based knowledge base is currently interacting with people at a rate of 100,000 inquiries per day. A unique web-based computer architecture (http://www.pandorabots.com) supporting the on-going development of the knowledge base is described. The... Read more

The notion of trust has been virtually absent from most work on how people assess and choose their information sources. Based on two empirical cases this study shows that software engineers and users of e-commerce websites devote a lot of attention to considerations about the trustworthiness of their sources, which include people, documents, and virtual agents. In the project-based software engineering environment trust tends to be a collaborative issue and the studied software engineers normally... Read more

The notion of trust has been virtually absent from most work on how people assess and choose their information sources. Based on two empirical cases this study shows that software engineers and users of e-commerce websites devote a lot of attention to considerations about the trustworthiness of their sources, which include people, documents, and virtual agents. In the project-based software engineering environment trust tends to be a collaborative issue and the studied software engineers normally... Read more

This paper discusses our vision of the future with respect to the introduction of virtual assistants in the e-market. It presents the latest evolution of the involvement framework, an on-going model aimed at driving the design and the evaluation of social agents  virtual characters designed to set up lasting relationships with the users. The framework is based on a review of the literature and on the systematic analysis of the firstgeneration social agents available... Read more