Towards Designing Enthusiastic AI Agents

Viegas, Carla; Alikhani, Malihe

doi:10.1145/3472306.3478366

Cited by 2 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The findings of this work contribute theoretical insights into the scant but emerging literature on the confluence between artificial voice's synthetic emotional expressions and learning (Fountoukidou et al, 2021;Hillaire et al, 2019;Viegas & Alikhani, 2021). From an instructional design perspective, this study offers practical recommendations to educators and instructional designers regarding using modern text-to-speech with artificial enthusiasm to narrate multimedia learning materials.…”

Section: Research Rationalementioning

confidence: 84%

I am Alexa, your virtual tutor!: The effects of Amazon Alexa’s text-to-speech voice enthusiasm in a multimedia learning environment

et al. 2022

View full text Add to dashboard Cite

Modern text-to-speech voices can convey social cues ideal for narrating multimedia learning materials. Amazon Alexa has a unique feature among modern text-to-speech vocalizers as she can infuse enthusiasm cues into her synthetic voice. In this first study examining modern text-to-speech voice enthusiasm effects in a multimedia learning environment, a between-subjects online experiment was conducted where learners from a large Asian university ( n = 244) listened to either Alexa’s: (1) neutral voice, (2) low-enthusiastic voice, (3) medium-enthusiastic voice, or (4) high-enthusiastic voice, narrating a multimedia lesson on distributed denial-of-service attack. While Alexa’s enthusiastic voices did not enhance persona ratings compared to Alexa’s neutral voice, learners could infer more enthusiasm expressed by Alexa’s medium-and high-enthusiastic voices than Alexa’s neutral voice. Regarding cognitive load, Alexa’s low-and high-enthusiastic voices decreased intrinsic and extraneous cognitive load ratings compared to Alexa’s neutral voice. While Alexa’s enthusiastic voices did not impact affective-motivational ratings differently from Alexa’s neutral voice, learners reported a significant increase of positive emotions from their baseline positive emotions after listening to Alexa’s medium-enthusiastic voice. Finally, Alexa’s enthusiastic voices did not enhance the learning performance on immediate retention and transfer tests compared to Alexa’s neutral voice. This study demonstrates that a modern text-to-speech voice enthusiasm can positively affect learners’ emotions and cognitive load during multimedia learning. Theoretical and practical implications are discussed through the lens of the Cognitive Affective Model of E-learning, Integrated-Cognitive Affective Model of Learning with Multimedia, and Cognitive Load Theory. We further outline this study’s limitations and recommendations for extending and widening the text-to-speech voice emotions research.

show abstract

Section: Research Rationalementioning

confidence: 84%

I am Alexa, your virtual tutor!: The effects of Amazon Alexa’s text-to-speech voice enthusiasm in a multimedia learning environment

et al. 2022

View full text Add to dashboard Cite

show abstract

“Hey Genie, You Got Me Thinking About My Menu Choices!”

Dubiel,

Leiva,

Bongard-Blanchy

et al. 2024

ACM Trans. Comput.-Hum. Interact.

View full text Add to dashboard Cite

Conversational agents (CAs) that deliver proactive interventions can benefit users by reducing their cognitive workload and improving performance. However, little is known regarding how such interventions would impact users’ reflection on choices in voice-only decision-making tasks. We conducted a within-subjects experiment to evaluate the effect of CA’s feedback delivery strategy at three levels (no feedback, unsolicited, and solicited feedback) and the impact on users’ likelihood of changing their choices in an interactive food ordering scenario. We discovered that in both feedback conditions the CA was perceived to be significantly more persuasive than in the baseline condition, while being perceived as significantly less confident. Interestingly, while unsolicited feedback was perceived as less appropriate than the baseline, both types of proactive feedback led participants to relisten and reconsider menu options significantly more often. Our results provide insights regarding the impact of proactive feedback on CA perception and user’s reflection in decision-making tasks, thereby paving a new way for designing proactive CAs.

show abstract

Towards Designing Enthusiastic AI Agents

Cited by 2 publications

References 29 publications

I am Alexa, your virtual tutor!: The effects of Amazon Alexa’s text-to-speech voice enthusiasm in a multimedia learning environment

I am Alexa, your virtual tutor!: The effects of Amazon Alexa’s text-to-speech voice enthusiasm in a multimedia learning environment

“Hey Genie, You Got Me Thinking About My Menu Choices!”

Contact Info

Product

Resources

About