Voice alone conveys the emotional tone of happy, content, and bored instructors as accurately as voice plus an embodied onscreen agent¶

Claim · All claims
Evidence · 1 study (3 entries) · causal r2 · q3
Currency · newest study 2022 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? For the happy instructor, the pattern of emotion ratings did not differ between the agent absent and agent present conditions. → Lawson 2022 q3 i? For the content instructor, the pattern of emotion ratings did not differ between the agent absent and agent present conditions. → Lawson 2022 (2) q3 i? For the bored instructor, the pattern of emotion ratings did not differ between the agent absent and agent present conditions. → Lawson 2022 (3)

Evidence¶

Lawson 2022¶

Lawson, A. P., & Mayer, R. E. (2022). The Power of Voice to Convey Emotion in Multimedia Instructional Messages. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-021-00282-y

q3 · i? · causal · r2

Repeated measures ANOVA on ratings of the happy instructor in the Mturk within-subjects experiment (agent present vs. agent absent × four emotion scales). The article reports "not a significant main effect of agent presence" and no interaction, consistent with the voice hypothesis.

"There was not a significant main effect of agent presence, F(1, 99) = 0.59, p = 0.443, nor an interaction, F(3, 297) = 0.39, p = 0.759."

Lawson 2022 (2)¶

Lawson, A. P., & Mayer, R. E. (2022). The Power of Voice to Convey Emotion in Multimedia Instructional Messages. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-021-00282-y

q3 · i? · causal · r2

Repeated measures ANOVA on ratings of the content instructor in the same within-subjects experiment. The article reports "no main effect of agent presence" and no interaction, consistent with the voice hypothesis.

"There was no main effect of agent presence, F(1, 99) = 1.70, p = 0.195, nor was there an interaction, F(3, 297) = 0.86, p = 0.464."

Lawson 2022 (3)¶

Lawson, A. P., & Mayer, R. E. (2022). The Power of Voice to Convey Emotion in Multimedia Instructional Messages. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-021-00282-y

q3 · i? · causal · r2

Repeated measures ANOVA on ratings of the bored instructor in the same within-subjects experiment. The article reports "no main effect of agent presence" and no interaction, consistent with the voice hypothesis.

"There was no main effect of agent presence, F(1, 99) = 0.40, p = 0.527, nor an interaction, F(3, 297) = 1.83, p = 0.143."

Discussion¶

Related Claims¶

• Recognizing a frustrated instructor's emotional tone required the embodied onscreen agent, contradicting the voice hypothesis for that emotion — related
• Participants rated happy and content instructors higher on positive than negative emotion scales, supporting the positivity hypothesis — related
• Participants detected emotional valence but did not distinguish between discrete emotions of the same valence — related
• Participants rated frustrated and bored instructors higher on negative than positive emotion scales, with the frustrated effect stronger when the agent was on screen — related