User attitude towards an embodied conversational agent: Effects of the interaction mode

Novielli, Nicole; Rosis, Fiorella de; Mazzotta, Irene

doi:10.1016/j.pragma.2009.12.016

Cited by 44 publications

(21 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We present two possible explanations for this phenomenon: First, anthropomorphism may happen unconsciously without the users' control or direct attention. As the literature shows that individuals speak intuitively [7] and that spoken interactions are more personal [26], it is likely that individuals do not deliberately anthropomorphize a VA, but still behave differently during the interaction. Second, the extant literature also shows that there are various ways to infer anthropomorphism [5]; voice output, without any visual component, may not be sufficient to provide the impression of a human being.…”

Section: Discussionmentioning

confidence: 99%

“…Compared to text input, speech is more intuitive [7] and requires less mental workload [6]. As a result, spoken interactions are more personal, they foster warmer user attitudes [26], and they encourage users to trust machines with more personal information [27]. In contrast, especially for high complexity tasks that may require user confirmation and control, text is preferred to voice [8].…”

Section: Voice Assistantsmentioning

confidence: 99%

See 1 more Smart Citation

Why Another Customer Channel? Consumers’ Perceived Benefits and Costs of Voice Commerce

Rzepka¹,

Berger²,

Heß³

2020

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Owing to rapidly increasing adoption rates of voice assistants (VAs), integrating voice commerce as a new customer channel is among the top objectives of businesses' current voice initiatives. However, customers are reluctant to use their VAs for shopping; a tendency not explained by extant literature. Therefore, this research aims to understand consumers' perceived benefits and costs when using voice commerce, based on a theoretical framework derived from prior literature and the theory of reasoned action. We evaluated and extended this framework by analyzing 30 semi-structured interviews with smart speaker users. According to our results voice commerce consumers perceive benefits in terms of efficiency, convenience, and enjoyment, and criticize the perceived costs of limited transparency, lack of trust, lack of control, and low technical maturity. The resulting model sheds light on the promoters and inhibitors of voice commerce and provides guidelines that enable practitioners to design and improve voice commerce applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Voice Assistantsmentioning

confidence: 99%

Why Another Customer Channel? Consumers’ Perceived Benefits and Costs of Voice Commerce

Rzepka¹,

Berger²,

Heß³

2020

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…In prior CA research, Litman et al [42] already added spoken language capabilities to text-based dialog tutors but were not able to reveal positive effects [41]. However, more recent research shows that if learners also verbalize their knowledge (e.g., also respond to the CA via voice), they are able to improve their learning process [36,53]. Thus, we propose:…”

Section: Cognitive Theory Of Multimedia Learningmentioning

confidence: 87%

Sara, the Lecturer: Improving Learning in Online Education with a Scaffolding-Based Conversational Agent

Winkler

Hobert

Salovaara

et al. 2020

Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Enrollment in online courses has sharply increased in higher education. Although online education can be scaled to large audiences, the lack of interaction between educators and learners is difficult to replace and remains a primary challenge in the field. Conversational agents may alleviate this problem by engaging in natural interaction and by scaffolding learners' understanding similarly to educators. However, whether this approach can also be used to enrich online video lectures has largely remained unknown. We developed Sara, a conversational agent that appears during an online video lecture. She provides scaffolds by voice and text when needed and includes a voice-based input mode. An evaluation with 182 learners in a 2 x 2 lab experiment demonstrated that Sara, compared to more traditional conversational agents, significantly improved learning in a programming task. This study highlights the importance of including scaffolding and voice-based conversational agents in online videos to improve meaningful learning.

show abstract

“…However, [144] found that the likeability of their ECA depended mainly on the agent's ability to answer the users requests appropriately, which shows the importance of building appropriate interaction strategies integrating deep analysis of user sentimentrelated phenomena for which mirroring may not be sufficiently complex. Besides, engagement policies that are coupled with user models [79,145] are required to vary their behavior in a more subtle way.…”

Section: Increasing the Agent Likeability And The Engagement Of The Usermentioning

confidence: 99%

Sentiment Analysis: From Opinion Mining to Human-Agent Interaction

Clavel

Callejas

2016

IEEE Trans. Affective Comput.

133

View full text Add to dashboard Cite

The opinion mining and human-agent interaction communities are currently addressing sentiment analysis from different perspectives that comprise, on the one hand, disparate sentiment-related phenomena and computational representations, and on the other hand, different detection and dialog management methods. In this paper we identify and discuss the growing opportunities for cross-disciplinary work that may increase individual advances. Sentiment/opinion detection methods used in human-agent interaction are indeed rare and, when they are employed, they are not different from the ones used in opinion mining and consequently not designed for socio-affective interactions (timing constraint of the interaction, sentiment analysis as an input and an output of interaction strategies). To support our claims, we present a comparative state of the art which analyzes the sentiment-related phenomena and the sentiment detection methods used in both communities and makes an overview of the goals of socio-affective human-agent strategies. We propose then different possibilities for mutual benefit, specifying several research tracks and discussing the open questions and prospects. To show the feasibility of the general guidelines proposed we also approach them from a specific perspective by applying them to the case of the Greta embodied conversational agents platform and discuss the way they can be used to make a more significative sentiment analysis for human-agent interactions in two different use cases: job interviews and dialogs with museum visitors.Index Terms-Sentiment analysis, opinion mining, embodied conversational agents (ECAs), human-agent interaction, affect, emotion, socio-affective interaction ! • C. Clavel is with the Institut Mines-Télécom, Télécom ParisTech,

show abstract

User attitude towards an embodied conversational agent: Effects of the interaction mode

Cited by 44 publications

References 12 publications

Why Another Customer Channel? Consumers’ Perceived Benefits and Costs of Voice Commerce

Why Another Customer Channel? Consumers’ Perceived Benefits and Costs of Voice Commerce

Sara, the Lecturer: Improving Learning in Online Education with a Scaffolding-Based Conversational Agent

Sentiment Analysis: From Opinion Mining to Human-Agent Interaction

Contact Info

Product

Resources

About