[5L2-OS-6a] OS-6

12:00 PM - 12:15 PM JST(3:00 AM - 3:15 AM UTC)

[5L2-OS-6a-01] Analysis of the Relationship Between Humor Points and Body Movements in Manzai Using Acceleration Sensors

〇Megumi Yasuo¹, Mayu Suzuki¹, Junjie Shan¹, Yoko Nishihara¹ (1. Ritsumeikan University)

Keywords:

Humor Detection,Multimodal Analysis,Body Movement Analysis

The objective of this study is to develop a technology for automatically annotating "humor points"—segments that an audience finds funny—within Manzai (traditional Japanese stand-up comedy) scripts. To achieve this, we analyzed the correlation between humor points and body movements detected by acceleration sensors. During the experiment, subjects watched Manzai performances while their body movement data were recorded via acceleration sensors. Simultaneously, emotion data were estimated from the subjects’ facial expressions. Humor points were defined as segments where the "Happy" emotion score exceeded a specific threshold. The analysis revealed that segments with high "Happy" scores significantly correlated with body movements of a certain magnitude or greater.