“I Like Your Shirt” - Dialogue Acts for Enabling Social Talk in Conversational Agents

Klüwer, Tina

doi:10.1007/978-3-642-23974-8_2

Cited by 22 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because latest ECAs can use their sophisticated multimodal communication abilities to establish rapport [Gratch et al 2006[Gratch et al , 2007aHuang et al 2011;Kang et al 2008aKang et al , 2008bMcQuiggan et al 2008;Pelachaud 2009;Prendinger and Ishizuka 2005;von der Pütten et al 2009;Gratch 2009, 2010], communicate empathically [Aylett et al 2007;Boukricha and Becker-Asano 2007;Boukricha and Wachsmuth 2011;Boukricha et al 2009;McQuiggan and Lester 2007;Ochs et al 2012;Prendinger and Ishizuka 2005] and engage in social talk [Bickmore and Giorgino 2006;Cassell and Bickmore 2003;Kluwer 2011;Schulman et al 2011], they have become capable of being as engaging as humans and have even been found more engaging than humans at times [Gratch et al 2007b].…”

Section: Embodied Conversational Agents (Ecas)mentioning

confidence: 98%

I Can Help You Change! An Empathic Virtual Agent Delivers Behavior Change Health Interventions

Lisetti

Amini

Yasavur

et al. 2013

ACM Trans. Manage. Inf. Syst.

165

141

View full text Add to dashboard Cite

We discuss our approach to developing a novel modality for the computer-delivery of Brief Motivational Interventions (BMIs) for behavior change in the form of a personalized On-Demand VIrtual Counselor (ODVIC), accessed over the internet. ODVIC is a multimodal Embodied Conversational Agent (ECA) that empathically delivers an evidence-based behavior change intervention by adapting, in real-time, its verbal and nonverbal communication messages to those of the user's during their interaction. We currently focus our work on excessive alcohol consumption as a target behavior, and our approach is adaptable to other target behaviors (e.g., overeating, lack of exercise, narcotic drug use, non-adherence to treatment). We based our current approach on a successful existing patient-centered brief motivational intervention for behavior change-the Drinker's Check-Up (DCU)-whose computer-delivery with a text-only interface has been found effective in reducing alcohol consumption in problem drinkers. We discuss the results of users' evaluation of the computer-based DCU intervention delivered with a text-only interface compared to the same intervention delivered with two different ECAs (a neutral one and one with some empathic abilities). Users rate the three systems in terms of acceptance, perceived enjoyment, and intention to use the system, among other dimensions. We conclude with a discussion of how our positive results encourage our long-term goals of on-demand conversations, anytime, anywhere, with virtual agents as personal health and well-being helpers.

show abstract

Section: Embodied Conversational Agents (Ecas)mentioning

confidence: 98%

I Can Help You Change! An Empathic Virtual Agent Delivers Behavior Change Health Interventions

Lisetti

Amini

Yasavur

et al. 2013

ACM Trans. Manage. Inf. Syst.

165

141

View full text Add to dashboard Cite

show abstract

“…Such agent repetitions lead to an unnatural interaction (Klüwer, 2011). To identify the agent's repeating responses, we measured similarity between agent's subsequent (not necessarily sequential) turns.…”

Section: Repeating Response Analysismentioning

confidence: 99%

Detecting Egregious Conversations between Customers and Virtual Agents

Sandbank

Shmueli-Scheuer

Herzig

et al. 2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

Virtual agents are becoming a prominent channel of interaction in customer service. Not all customer interactions are smooth, however, and some can become almost comically bad. In such instances, a human agent might need to step in and salvage the conversation. Detecting bad conversations is important since disappointing customer service may threaten customer loyalty and impact revenue. In this paper, we outline an approach to detecting such egregious conversations, using behavioral cues from the user, patterns in agent responses, and useragent interaction. Using logs of two commercial systems, we show that using these features improves the detection F1-score by around 20% over using textual features alone. In addition, we show that those features are common across two quite different domains and, arguably, universal.

show abstract

“…Several other agents which make use of social dialogue (small talk) have been developed to date, using hand-crafted strategies (cf. [24] for an overview). [24] pioneered the use of a functionally-motivated taxonomy of small talk dialogue acts based on the social science theory of face and extracted dialogue act sequences for social talk from an annotated corpus.…”

Section: Introductionmentioning

confidence: 98%

“…[24] for an overview). [24] pioneered the use of a functionally-motivated taxonomy of small talk dialogue acts based on the social science theory of face and extracted dialogue act sequences for social talk from an annotated corpus. [5] on the other hand, analysed a corpus of child-adult conversations to extract so-called personalization behaviors.…”

Section: Introductionmentioning

confidence: 98%

Effects of off-activity talk in human-robot interaction with diabetic children

Kruijff-Korbayová

Oleari²,

Baroni³

et al. 2014

The 23rd IEEE International Symposium on Robot and Human Interactive Communication

View full text Add to dashboard Cite

This paper presents the results from an experiment with a conversational human-robot interaction system aimed at long-term support for diabetic children. The system offers a set of activities aimed to help a child to improve its capability to manage diabetes. There is a large body of literature on the techniques that artificial agents can use to establish and maintain long-term social-emotional relationships with their users. The novel aspect in the present study is the inclusion of off-activity talk interspersed within talk pertaining the activity at hand and aimed to elicit the child's self-disclosure. The children in our study (N=20, age 11-14) were more interested to have another session with the robot when their interaction included also off-activity talk, even though there was no difference in the perception of the robot by the children between the groups with and without off-activity talk. Furthermore, individual interactions with the robot positively influenced the children's adherence to a therapy-related requirement, namely the filling in of a nutritional diary.

show abstract

“I Like Your Shirt” - Dialogue Acts for Enabling Social Talk in Conversational Agents

Cited by 22 publications

References 15 publications

I Can Help You Change! An Empathic Virtual Agent Delivers Behavior Change Health Interventions

I Can Help You Change! An Empathic Virtual Agent Delivers Behavior Change Health Interventions

Detecting Egregious Conversations between Customers and Virtual Agents

Effects of off-activity talk in human-robot interaction with diabetic children

Contact Info

Product

Resources

About