Computer Science

On Multimodal Emotion Recognition for Human-Chatbot Interaction in the Wild

N. Kovačević, M. Gross, et al.

A study conducted by Nikola Kovačević, Markus Gross, Christian Holz, and Rafael Wampfler collected multimodal text, audio, and video from 99 participants interacting with a GPT-3 chatbot over three weeks, uncovering a strong domain gap between human-human and human-chatbot emotion signals and showing personalization can boost recognition by up to 38–41%.

00:00

~3 min • Beginner • English

Related Publications

Explore these studies to deepen your understanding of the subject.

Interdisciplinary Studies

The concept of "interaction" in debates on human-machine interaction

S. Schleidgen, O. Friedrich, et al.

Health and Fitness

Considerations on the human Achilles tendon moment arm for in vivo triceps surae muscle-tendon unit force estimates

D. Holzer, F. K. Paternoster, et al.

Education

Not-for-profit or for-profit? Research on the high-quality development path of private universities in China based on system dynamics

S. Duan, H. Yang, et al.

Social Work

Democratizing the discourse on criminal justice in social media: the activity for justice for Roman Zadorov as a case study

A. Lev-on

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny