conversational agent Papers

This research investigates the meaning of ‘human-computer relationship’ and presents techniques for constructing, maintaining, and evaluating such relationships, based on research in social psychology, sociolinguistics, communication and other social sciences. Contexts in which relationships are particularly important are described, together with specific benefits (like trust) and task outcomes (like improved learning) known to be associated with relationship quality. We especially consider the problem of designing for longterm interaction, and define relational agents as computational... Read more

This paper describes an application of the conversational agent Max in a real-world setting. The agent is employed as guide in a public computer museum, where he engages with visitors in natural face-to-face communication, provides them with information about the museum or the exhibition, and conducts natural small talk conversations. The design of the system is described with a focus on how the conversational behavior is achieved. Logfiles from interactions between Max and museum visitors were... Read more

The objective of this chapter is to identify the common knowledge and practice in research methodology and to apply it to the field of software evaluation, especially of embodied conversational agents. Relevant issues discussed are: how to formulate a good research question, what research strategy to use, which data collection methods are most appropriate and how to select the right participants. Reliability and validity of the data sets are dealt with and finally the chapter... 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

A chatbot named Freudbot was constructed using the open source architecture of AIML to determine if a famous person application of chatbot technology could improve student-content interaction in distance education. Fifty-three students in psychology completed a study in which they chatted with Freudbot over the web for 10 minutes under one of two instructional sets. They then completed a questionnaire to provide information about their experience and demographic variables. The results from the questionnaire indicated... Read more

We studied the role of the competence of an interface agent that helped users to learn and use a text editor. Participants in the study made a set of changes to a document with the aid of one of four interface agents. The agent would respond to participants’ spoken questions as well as make proactive suggestions using a synthesized voice. The agents varied in the quality of responses and... Read more

Individuality of Embodied Conversational Agents (ECAs) may depend on both the look of the agent and the way it combines different modalities such as speech and gesture. In this chapter, we describe a study in which male and female users had to listen to three short technical presentations made by ECAs. Three multimodal strategies of ECAs for using arm gestures with speech were compared: redundancy, complementarity, and speech-specialization. These strategies were randomly attributed to different-looking... Read more

The main reason for bringing life-like characters onto the internet is commercial. They may attract users to a particular page and encourage them to log on more often and/or stay longer than otherwise in the application. This is of course advantageous for providers selling advertising. In the following we describe Flirtboat, a commercial multi-user application for the internet where users design their representatives and send them off to a virtual community (a net environment), and we... Read more

There are currently no evaluation methods specific to ECAs in CVEs and traditional evaluation methods are limited in their applicability and consequently unlikely to address the full range of aspects now inherent in such systems. We argue that a combination of controlled experimentation, quasi-experiments, review-based evaluation and heuristic expert reviews is needed. To operationalise these traditional evaluation methods the concept of presence was deployed, and it was argued that presence as a cognitive variable can... Read more

This paper extends our previous work which demonstrated that social dialogue can have a significant impact on a user's trust of an ECA, by investigating whether these results hold in the absence of nonverbal cues. We present the results of a study designed to determine whether the psychological effects of social dialogue – namely to increase trust and associated positive evaluations - vary when the nonverbal cues provided by the embodied conversational agent are... Read more