Evaluating a realistic agent in an advice-giving task

Berry, Dianne C.; Butler, Laurie; Rosis, Fiorella de

doi:10.1016/j.ijhcs.2005.03.006

Cited by 90 publications

(69 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is to keep the system simple. As inconsistency between emotion and content is undesireable (Berry et al, 2005), we avoided this by the simple expedient of choosing system utterances that would be compatible with any emotional coloring.…”

Section: Dialog Manager and Speech Recognizermentioning

confidence: 99%

Achieving rapport with turn-by-turn, user-responsive emotional coloring

Acosta

Ward

2011

Speech Communication

View full text Add to dashboard Cite

People in dialog use a rich set of nonverbal behaviors, including variations in the prosody of their utterances. Such behaviors, often emotion-related, call for appropriate responses, but today's spoken dialog systems lack the ability to do this. Recent work has shown how to recognize user emotions from prosody and how to express system-side emotions with prosody, but demonstrations of how to combine these functions to improve the user experience have been lacking. Working with a corpus of conversations with students about graduate school, we analyzed the emotional states of the interlocutors, utterance by utterance, using three dimensions: activation, evaluation, and power. We found that the emotional coloring of the speaker's utterance could be largely predicted from the emotion shown by her interlocutor in the immediately previous utterance. This finding enabled us to build Gracie, the first spoken dialog system that recognizes a user's emotional state from his or her speech and gives a response with appropriate emotional coloring. Evaluation with 36 subjects showed that they felt significantly more rapport with Gracie than with either of two controls. This shows that dialog systems can tap into this important level of interpersonal interaction using today's technology.

show abstract

Section: Dialog Manager and Speech Recognizermentioning

confidence: 99%

Achieving rapport with turn-by-turn, user-responsive emotional coloring

Acosta

Ward

2011

Speech Communication

View full text Add to dashboard Cite

show abstract

“…The results from previous studies indicate that the use of an ECA can have a positive effect on how the feedback is received by the user in behaviour change support systems. This can eventually lead to a better performance of the coaching program in the future and a more effective way to support users to change their behaviour (Schulman & Bickmore 2009;Blanson Henkemans et al 2009;Berry et al 2005). The results of this user evaluation and the effect of adding an ECA to the UI are subject of future user evaluations with a working prototype of the system.…”

Section: Future Workmentioning

confidence: 96%

Glanceability Evaluation of a Physical Activity Feedback System for Office Workers

Boerema¹,

Klaassen

Akker

et al. 2012

Proceedings of the Sixth International Symposium on E-Health Services and Technologies and the Third International Conference O

View full text Add to dashboard Cite

Abstract:This paper presents the results of a user evaluation to design a glanceable user interface presenting physical activity feedback to office workers during the workday. The feedback is presented on a central and public display next to the coffee machine in the office building. Users should be able to receive the feedback quickly and easily while getting a cup of coffee − the user interface should be glanceable. The feedback should communicate the (real-time) amount of physical activity and the progress toward the goal of the user for a day. Three mock-ups of user interfaces were developed and evaluated in a user evaluation study. Differences on reaction time and user preferences were found. None of these results were significant. Adding group information to the mock-up increases reaction time and therefore lowers the glanceability negatively.

show abstract

“…An interface agent is, more generally, a computer-generated character designed to interact with users by simulating human appearance and behaviors through artificial intelligence. Dependent on their function, they are referred to as Virtual Customer Service Agent [ 15], Product Recommendation Agent [ 6], Embodied Conversational Agent [ 11], [ 17], Pedagogical Agent [ 18], [19][20][21], [31], or as a human-like or embodied agent/character [12][13], [23][24][25][26][27].…”

Section: Introductionmentioning

confidence: 99%

Gendering the Machine: Preferred Virtual Assistant Gender and Realism in Self-Service

Payne

Szymkowiak

Robertson

et al. 2013

Intelligent Virtual Agents

View full text Add to dashboard Cite

Abstract.A virtual agent is a human-like character that is designed to assist users in interactions with technology and virtual worlds. Research into the preferred visual characteristics of a virtual agent has focused on education-based agents, gaming avatars, and online help assistants. However, findings from these studies are not necessarily generalizable to other technologies, such as self-service checkouts (SSCO). This paper describes data from 578 participants, looking at the gender preferences of Virtual Assistants (VA) in a SSCO context and the impact of VA realism depending on user gender. Due to female participants' preference for female VAs, and an overall preference for threedimensional characters, a realistic, female VA should be used in SSCO. The results are discussed in terms of similarity-attraction theory and social role theory.

show abstract

Evaluating a realistic agent in an advice-giving task

Cited by 90 publications

References 23 publications

Achieving rapport with turn-by-turn, user-responsive emotional coloring

Achieving rapport with turn-by-turn, user-responsive emotional coloring

Glanceability Evaluation of a Physical Activity Feedback System for Office Workers

Gendering the Machine: Preferred Virtual Assistant Gender and Realism in Self-Service

Contact Info

Product

Resources

About