A Taxonomy of Social Cues for Conversational Agents

Feine, Jasper; Gnewuch, Ulrich; Morana, Stefan; Maedche, Alexander

doi:10.1016/j.ijhcs.2019.07.009

Cited by 355 publications

(283 citation statements)

References 105 publications

Supporting

Mentioning

276

Contrasting

Unclassified

Order By: Relevance

“…Related to the third dimension, verbal cues, Schuetzler et al (2014) for example found that even modest adjustments to an agents responses with regard to syntax and word variability lead to a more positive evaluation of a CA. Overall, these and similar experiments highlight a variety of social cues that is available to make a CA's appearance and behavior as human-like as possible (Feine et al 2019).…”

Section: Conversational Capabilitiesmentioning

confidence: 53%

“…From a design perspective, a variety of social cues for CAs is available to trigger social responses and stimulate perceptions of anthropomorphism (Feine et al 2019). However, while many of these cues can be incorporated in the design with relatively low effort, such as giving the CA a human name (Cowell and Stanney 2005) or using response delays to simulate thinking and typing of a CA (Gnewuch et al 2018), sustaining a human-like interaction in an evolving conversation represents a major design challenge.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Designing Anthropomorphic Enterprise Conversational Agents

2020

View full text Add to dashboard Cite

The increasing capabilities of conversational agents (CAs) offer manifold opportunities to assist users in a variety of tasks. In an organizational context, particularly their potential to simulate a human-like interaction via natural language currently attracts attention both at the customer interface as well as for internal purposes, often in the form of chatbots. Emerging experimental studies on CAs look into the impact of anthropomorphic design elements, so-called social cues, on user perception. However, while these studies provide valuable prescriptive knowledge of selected social cues, they neglect the potential detrimental influence of the limited responsiveness of present-day conversational agents. In practice, many CAs fail to continuously provide meaningful responses in a conversation due to the open nature of natural language interaction, which negatively influences user perception and often led to CAs being discontinued in the past. Thus, designing a CA that provides a human-like interaction experience while minimizing the risks associated with limited conversational capabilities represents a substantial design problem. This study addresses the aforementioned problem by proposing and evaluating a design for a CA that offers a human-like interaction experience while mitigating negative effects due to limited responsiveness. Through the presentation of the artifact and the synthesis of prescriptive knowledge in the form of a nascent design theory for anthropomorphic enterprise CAs, this research adds to the growing knowledge base for designing humanlike assistants and supports practitioners seeking to introduce them into their organizations.

show abstract

Section: Conversational Capabilitiesmentioning

confidence: 53%

Section: Introductionmentioning

confidence: 99%

Designing Anthropomorphic Enterprise Conversational Agents

2020

View full text Add to dashboard Cite

show abstract

“…Diverse scientific articles examine the design and engineering of chatbots from different technical perspectives, e.g., emotional intelligence (e.g., Feine et al 2019) or anthropomorphic features (Kim et al 2018), and others focus on the study of chatbots in particular application domains (e.g., Bittner et al 2019). Gnewuch et al (2017) provide a basic classification of chatbots based on two dimensions named as ''context'' and ''primary mode of communication''.…”

Section: Overview Of Related Chatbot Literaturementioning

confidence: 99%

“…Diederich et al (2019) classify 51 platforms of chatbots into eleven dimensions. Feine et al (2019) concentrate on building a taxonomy of social cues of CA focused on verbal, visual, auditory and invisible aspects. However, a comprehensive and empirically tested chatbot taxonomy for domain-specific chatbots, integrating scientific and practical knowledge into different classes or groups, is still missing.…”

Section: Overview Of Related Chatbot Literaturementioning

confidence: 99%

“…The chatbots in archetype E (e.g., Smarty Simple Mind chatbot) are characterized by 89% showing a high socio-emotional behavior and all chatbots being proactive in the human-computer dialogue by asking specific context-relevant questions. This can be associated with the AI-based emotional intelligence of chatbots described in the literature (e.g., Feine et al 2019).…”

Section: Chatbot Archetypesmentioning

confidence: 99%

See 1 more Smart Citation

Virtual Assistance in Any Context

et al. 2020

View full text Add to dashboard Cite

Several domain-specific assistants in the form of chatbots have conquered many commercial and private areas. However, there is still a limited level of systematic knowledge of the distinctive characteristics of design elements for chatbots to facilitate development, adoption, implementation, and further research. To close this gap, the paper outlines a taxonomy of design elements for chatbots with 17 dimensions organized into the perspectives intelligence, interaction and context. The conceptually grounded design elements of the taxonomy are used to analyze 103 chatbots from 23 different application domains. Through a clustering-based approach, five chatbot archetypes that currently exist for domain-specific chatbots are identified. The developed taxonomy provides a structure to differentiate and categorize domain-specific chatbots according to archetypal qualities that guide practitioners when taking design decisions. Moreover, the taxonomy serves academics as a foundation for conducting further research on chatbot design while integrating scientific and practical knowledge.Keywords Chatbot taxonomy Á Design elements Á Domain-specific chatbots Á Human computer interaction Bus Inf Syst Eng 62(3): 211-225 (2020)

show abstract

Student therapists' experiences of learning using a machine client: A proof‐of‐concept exploration of an emotionally responsive interactive client (ERIC)

Prescott,

Ogilvie,

Hanley

2023

Couns and Psychother Res

View full text Add to dashboard Cite

BackgroundThe use of artificial intelligence (AI) is increasing in many areas of healthcare, including mental healthcare. The automated nature of such technologies has the potential to be developed to work with large numbers of people. This paper examines the way that student therapists experience using an interactive text‐based machine client as a training tool.MethodologyChatbot technology has been used to develop an emotionally responsive interactive client (ERIC). This introduces individuals to concepts of person‐centred therapy (empathy, congruence and unconditional positive regard) by using a series of pre‐programmed scenarios. Twenty‐eight student therapists evaluated ERIC's potential as a learning tool. Individuals were recruited from one university from a postgraduate and an undergraduate counselling programme.FindingsFeedback was generally positive, with all reporting that they enjoyed engaging with ERIC as a learning method. ERIC helped individuals consider their understanding of counselling skills in a non‐judgemental environment. Participants felt the scenarios were realistic and engaging, with many reporting that they felt they were engaging with a real client/person due to ERIC's ability to express emotions.DiscussionERIC is at the proof‐of‐concept phase. From the feedback presented here, it is evident that it can be a useful learning tool. Further development of ERIC with feedback from a larger sample is, however, required. ERIC is currently a text‐based client, and further development would like to see the intervention be voice‐activated to enhance the experience. ERIC can be further enhanced and adapted to be a useful learning platform for student therapists, as well as for students in other (healthcare‐related) disciplines, whereby a client or patient is required.

show abstract

A Taxonomy of Social Cues for Conversational Agents

Cited by 355 publications

References 105 publications

Designing Anthropomorphic Enterprise Conversational Agents

Designing Anthropomorphic Enterprise Conversational Agents

Virtual Assistance in Any Context

Student therapists' experiences of learning using a machine client: A proof‐of‐concept exploration of an emotionally responsive interactive client (ERIC)

Contact Info

Product

Resources

About