Find the Bot!: Gamifying Facial Emotion Recognition for Both Human Training and Machine Learning Data Collection

要旨

Facial emotion recognition (FER) constitutes an essential social skill for both humans and machines to interact with others. To this end, computer interfaces serve as valuable tools for training individuals to improve FER abilities, while also serving as tools for gathering labels to train FER machine learning datasets. However, existing tools have limitations on the scope and methods of training non-clinical populations and also on collecting labels for machines. In this study, we introduce Find the Bot!, an integrated game that effectively engages the general population to support not only human FER learning on spontaneous expressions but also the collection of reliable judgment-based labels. We incorporated design guidelines from gamification, education, and crowdsourcing literature to engage and motivate players. Our evaluation (N=59) shows that the game encourages players to learn emotional social norms on perceived facial expressions with a high agreement rate, facilitating effective FER learning and reliable label collection all while enjoying gameplay.

著者
Yeonsun Yang
DGIST, Daegu, Korea, Republic of
Ahyeon Shin
DGIST, Daegu, Korea, Republic of
Nayoung Kim
DGIST, Daegu, Korea, Republic of
Huidam Woo
DGIST, Daegu, Korea, Republic of
John Joon Young. Chung
Midjourney, San Francisco, California, United States
Jean Y. Song
DGIST, Daegu, Korea, Republic of
論文URL

https://doi.org/10.1145/3613904.3642880

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Game Design A

316B
4 件の発表
2024-05-15 01:00:00
2024-05-15 02:20:00