Relational Agents: A Critical Review

Campbell, Robert; Grimshaw, Mark; Green, Gill

doi:10.2174/1875323x00901010001

Cited by 18 publications

(19 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bickmore [7] introduced and explored the concept of "relational agents", namely ECAs designed to form long-term social-emotional relationships with their users. Relational agents are distinct from other types of social agents in their ability to imitate the way people incrementally get to know and trust each other through conversations [11]. They maintain a memory of specific interactions, with the intention of recalling and referring to them later so as to evolve relationships with their users [7].…”

Section: Embodied Conversational Agents (Ecas)mentioning

confidence: 99%

Virtual Assistive Companions for Older Adults: Qualitative Field Study and Design Implications

Tsiourti¹,

Joly²,

Wings³

et al. 2014

Proceedings of the 8th International Conference on Pervasive Computing Technologies for Healthcare

View full text Add to dashboard Cite

This paper presents a qualitative study conducted to explore perceptions, attitudes and expectations for a virtual assistive companion designed to supplement human caregiving and facilitate an improved quality of life and long-term health benefits for older adults. The study was conducted adopting a human-centred approach; employing focus groups and individual interviews with older adults, professional caregivers and psychologists specialized in the aging process. Results indicated that users were in favour of a virtual companion and highlighted its potential to assist the accomplishment of daily activities and make more efficient use of human care services. Humanlike communication and behaviour were desirable whereas mixed opinions were expressed about humanlike appearance. The ramifications of the study are discussed in the form of design implications for the development of a virtual assistive companion that possesses the appropriate "social skills" to establish and maintain comfortable and acceptable longterm interaction and offers "useful" support to older adults. Categories and Subject Descriptors General TermsDesign, Human Factors, Measurement. KeywordsHuman-centred design, older users, qualitative field study, health promotion, personalization, HCI. INTRODUCTION 1.The increasing demand for healthcare and quality of life services to support the aging population has inspired researchers worldwide to explore the applicability of new intelligent technologies to support older adults to cope with the challenges of aging, live more independently and make more efficient use of care services. While human caregiving cannot and will not be replaced, assistive technologies have the potential to supplement human caregiving and to improve the quality of life for both older adults and their caregivers [25]. A range of computer-based techniques has been used in the design of advanced assistive technologies focused on "aging in place"; that is to enable older adults to remain in their homes for longer periods and help those who are in assisted living care facilities to maintain more independence there. Virtual computer-animated characters, also known as Embodied Conversational Agents (ECAs) [12], have attracted a lot of attention over the past years and have been successfully used in health interventions, including several designed specifically for older users [2,8,26,30]. ECAs move beyond the paradigm of computer as a tool and allow for multimodal interaction reflecting natural human-to-human communication. Recent research has shown that ECAs expressing empathetic emotions have the potential to enhance user's satisfaction, engagement [18] and performance in task achievement [23].In the scope of the European project CaMeLi [10], we investigate the use of ECAs as long-term assistive companions for older adults (aged 65 and above). In this context, we define a successful "virtual assistive companion" as an agent that is seamlessly integrated into the living environment and follows the daily life patterns of its use...

show abstract

Section: Embodied Conversational Agents (Ecas)mentioning

confidence: 99%

Virtual Assistive Companions for Older Adults: Qualitative Field Study and Design Implications

Tsiourti¹,

Joly²,

Wings³

et al. 2014

Proceedings of the 8th International Conference on Pervasive Computing Technologies for Healthcare

View full text Add to dashboard Cite

show abstract

“…However, they are mainly developed for a specific purpose and in a specific context. In [12] the authors propose an overview of the different areas in which relational agents could be used. Most of them are thus used in applications related to health and behavioral change, but one can also find them in leisure and domestic applications, or even in video games.…”

Section: B Relational Agentsmentioning

confidence: 99%

Toward a Computational Model of Social Relations for Artificial Companions

Pecune

2013

2013 Humaine Association Conference on Affective Computing and Intelligent Interaction

View full text Add to dashboard Cite

“…The relationship between agent and interlocutor has shown to be improved when the agent engages in Small Talk (Campbell et al, 2009). But, the complex structure of Small Talk has been mostly neglected.…”

Section: Motivationmentioning

confidence: 99%

WHO ARE YOU? - On the Acquisition of Information about People for an Agent that Remembers

Mattar

Wachsmuth

2012

Proceedings of the 4th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

Abstract:Humans make extensive use of specialized representations to remember people they interacted with. While current research on embodied conversational agents focuses on the relationship between agent and interlocutor, the representation of the latter is mostly neglected. But information about others are inevitable for an agent to adapt to its interlocutors and to establish long-term relationships with them. In this work, we present a model of Person Memory for virtual agents. We discuss what kinds of information have to be stored about people. Furthermore, we stress the importance of social categories. In our scenario, we focus on first encounters between our agent and people. We show how the agent is able to exploit his Person Memory to acquire information about others during Small Talk and guide the conversation. MOTIVATIONWhen two people meet for the first time they often would like to know from each other: Who are you? How do humans acquire information of others they encounter for the first time? How and what information do they remember from each other? Research on human-like memory for virtual agents has gained a lot of attention recently. Agents equipped with autobiographical memory, e.g. (Kasap et al., 2009), or episodic memory, cf. (Brom et al., 2007, are enabled to remember their own experiences. Companion agents greatly benefit from these memories, in that information from previous interactions can be accessed and used by the agent. However, in the above approaches the memories are centered on the agent's experiences, yet people the agent interacted with play a minor role.In this work we present a model of Person Memory for an embodied conversational agent that focuses on the representation of people. Our agent MAX has a cognitive architecture based on BDI. The agent resides on the hallway of the AI group of Bielefeld University. A broad range of Small Talk knowledge allows for short enjoyable interactions with him. But over the long run, conversations with our agent are more or less the same. So it is not easy to build up some kind of relationship over time, since people may get annoyed by repetitive interactions. To enable our agent to build up longer lasting relationships, he should be put in the position to adapt to his interlocutors. In that, he must be able to distinguish between different kinds of people, in order to know what to talk about. To remember past interactions would allow him to avoid repetition of things already said, and to pick up interesting topics of previous conversations.Small Talk is considered important to increase trust and familiarity (Bickmore and Cassell, 2001) between virtual agents and their interaction partners. Yet, most of the systems equipped with small-talk abilities are restricted to common topics, like the current weather. Small Talk about topics of interest to certain individuals has been mostly neglected. In this paper, we show how information of social categories can be exploited in order to acquire information about, and guide a conversation with, a n...

show abstract

Relational Agents: A Critical Review

Cited by 18 publications

References 25 publications

Virtual Assistive Companions for Older Adults: Qualitative Field Study and Design Implications

Virtual Assistive Companions for Older Adults: Qualitative Field Study and Design Implications

Toward a Computational Model of Social Relations for Artificial Companions

WHO ARE YOU? - On the Acquisition of Information about People for an Agent that Remembers

Contact Info

Product

Resources

About